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. 24233
    Prev
    Next
    INDEX
    Explanations

    Holocaust denial

    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
    ಿಐ
    -0.08
    .Symbol
    -0.08
     prioridades
    -0.08
     ವಿನ
    -0.08
    .Ribbon
    -0.07
     bulls
    -0.07
    mentation
    -0.07
     Meridian
    -0.07
     suivi
    -0.07
    (pop
    -0.07
    POSITIVE LOGITS
     harmful
    0.08
    odie
    0.08
    lüsse
    0.08
     автомобиль
    0.07
     debate
    0.07
     basal
    0.07
     fud
    0.07
     അപകട
    0.07
    机动车
    0.07
    곡
    0.07
    Activations Density 0.002%

    No Known Activations