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. 90558
    Prev
    Next
    INDEX
    Explanations

    violence

    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
     hubiese
    -0.08
     snug
    -0.08
     superb
    -0.08
    zijn
    -0.08
     counselor
    -0.08
    _payment
    -0.08
     న
    -0.07
    Pays
    -0.07
    _MC
    -0.07
     നെ
    -0.07
    POSITIVE LOGITS
     violence
    0.12
     violência
    0.09
     violencia
    0.09
     sanctioned
    0.08
    uous
    0.08
     Gewalt
    0.08
     Violence
    0.08
     violently
    0.08
     violent
    0.08
     Andrew
    0.08
    Activations Density 0.034%

    No Known Activations