© 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. 7-RESID-POST-AA
    11. 1298
    Prev
    Next
    INDEX
    Explanations

    do

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enville
    -0.09
    Gar
    -0.07
    的数据
    -0.07
     crossover
    -0.07
    enced
    -0.07
    apal
    -0.07
     prêmio
    -0.07
     Legends
    -0.07
     Gestaltung
    -0.07
     dyst
    -0.07
    POSITIVE LOGITS
     ello
    0.09
     ذلك
    0.09
     Lui
    0.08
     willen
    0.08
     Ars
    0.08
    _assets
    0.08
     것입니다
    0.07
    Realtime
    0.07
     benut
    0.07
     Fellows
    0.07
    Activations Density 0.042%

    No Known Activations