Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43663
    Prev
    Next
    INDEX
    Explanations

    sexual assault

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _OB
    -0.09
     entertained
    -0.07
    FUN
    -0.07
    Func
    -0.07
    Sesion
    -0.07
     mortality
    -0.07
    Ob
    -0.07
    -0.07
    (cache
    -0.07
    Compile
    -0.07
    POSITIVE LOGITS
     rape
    0.15
     perpetr
    0.13
     raped
    0.12
    侵犯
    0.11
     perpetrators
    0.11
     sexual
    0.11
     assault
    0.11
     sexu
    0.10
     сексу
    0.10
     prostit
    0.10
    Activations Density 0.047%

    No Known Activations