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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 91151
    Prev
    Next
    INDEX
    Explanations

    ,

    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
     domínio
    -0.09
     적
    -0.08
     સરળ
    -0.08
     Mead
    -0.08
    adura
    -0.07
     ساده
    -0.07
    -is
    -0.07
    ವಾಗಿದೆ
    -0.07
     ಸರ
    -0.07
     Gart
    -0.07
    POSITIVE LOGITS
     female
    0.09
     العزيز
    0.09
     collectif
    0.09
     defending
    0.09
     male
    0.09
     females
    0.09
    Male
    0.09
    Avatar
    0.09
     femen
    0.08
     представители
    0.08
    Activations Density 0.034%

    No Known Activations