© 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. 99153
    Prev
    Next
    INDEX
    Explanations

    opponents

    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
     aph
    -0.08
     వారికి
    -0.08
    ,
    -0.08
    (light
    -0.08
    Untuk
    -0.08
    .Rem
    -0.08
     بشأن
    -0.07
    (non
    -0.07
     Belgische
    -0.07
     Austrian
    -0.07
    POSITIVE LOGITS
    minster
    0.09
    kap
    0.08
     respet
    0.08
    egg
    0.08
     Album
    0.08
     Kap
    0.08
     respected
    0.08
    elik
    0.07
     kapit
    0.07
     Shelf
    0.07
    Activations Density 0.000%

    No Known Activations