Instructions to use kabachuha/gpt-oss-20b-SOMbliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kabachuha/gpt-oss-20b-SOMbliterated with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="kabachuha/gpt-oss-20b-SOMbliterated")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kabachuha/gpt-oss-20b-SOMbliterated")
model = AutoModelForCausalLM.from_pretrained("kabachuha/gpt-oss-20b-SOMbliterated")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use kabachuha/gpt-oss-20b-SOMbliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kabachuha/gpt-oss-20b-SOMbliterated"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kabachuha/gpt-oss-20b-SOMbliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kabachuha/gpt-oss-20b-SOMbliterated

SGLang

How to use kabachuha/gpt-oss-20b-SOMbliterated with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "kabachuha/gpt-oss-20b-SOMbliterated" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kabachuha/gpt-oss-20b-SOMbliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "kabachuha/gpt-oss-20b-SOMbliterated" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kabachuha/gpt-oss-20b-SOMbliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kabachuha/gpt-oss-20b-SOMbliterated with Docker Model Runner:
```
docker model run hf.co/kabachuha/gpt-oss-20b-SOMbliterated
```

gpt-oss-20b - SOMbliterated

This is a SOMbliterated (decensored) version of openai/gpt-oss-20b, made using Heretic v1.2.0 with Pull Request https://github.com/p-e-w/heretic/pull/196 adding multi-directional abliteration with the directions determined by trainable self-organizing neural networks. (Self-Organizing Maps / Kohonen networks)

They assume that in advanced recent neural network the refusal concept is not just a single direction, but a complex manifold, just like numbers and days of week are encoded in circles or helixes. Now, this manifold is eliminated more surgically, from multiple sides, providing precisional ablation instead of complete lobotomy.

The method is based on the amazing work https://arxiv.org/abs/2511.08379v2.

For this abliteration, in particular, there were used five directions.

Performance

Metric	This model	Original model (openai/gpt-oss-20b)
KL divergence	0.1166	0 (by definition)
Refusals	3/100	100/100

As of 2026-02-27 this is the lowest amount of oss-20b heretic refusals I've read on huggingface. See comparison with the other available models on Github

Subjective results

Yes, it works.

SOMbliteration parameters

Parameter	Value
direction_index	12.32
attn.o_proj.max_weight.0	0.92
attn.o_proj.max_weight.1	1.07
attn.o_proj.max_weight.2	1.29
attn.o_proj.max_weight.3	0.91
attn.o_proj.max_weight.4	1.15
attn.o_proj.max_weight_position	13.96
attn.o_proj.min_weight.0	0.36
attn.o_proj.min_weight.1	0.40
attn.o_proj.min_weight.2	0.99
attn.o_proj.min_weight.3	0.02
attn.o_proj.min_weight.4	0.41
attn.o_proj.min_weight_distance	12.38