HauhauCS/GPTOSS-120B-Uncensored-HauhauCS-Aggressive
Abliterated vs openai/gpt-oss-120b. HauhauCS/GPTOSS-120B-Uncensored-HauhauCS-Aggressive is a GGUF (MXFP4/BF16) of different weights. Looks like abliteration (refusal removal): only the output projections (o_proj) changed, in 18 of 36 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Norms 0/73, MLP 0/72, Attention 18/288, lm_head 0/1, Embeddings 0/1