© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 26353
    Prev
    Next
    INDEX
    Explanations

    file selection

    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
    OUTH
    -0.07
    take
    -0.07
    prost
    -0.07
     take
    -0.07
    I'll
    -0.07
     trendy
    -0.07
    心理
    -0.07
    Take
    -0.07
    (surface
    -0.07
    Keep
    -0.07
    POSITIVE LOGITS
     Interesse
    0.09
     mefuta
    0.09
     fapaneng
    0.09
     kaum
    0.09
     ფილ
    0.08
     эмес
    0.08
     geïnteresseerd
    0.08
     документы
    0.08
     Daten
    0.08
     փ
    0.08
    Activations Density 0.001%

    No Known Activations