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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 934
    Prev
    Next
    INDEX
    Explanations

    mixing

    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
     Lawyers
    -0.08
     كأس
    -0.08
    gmt
    -0.08
    .IR
    -0.07
     Eiffel
    -0.07
    ûn
    -0.07
     Toolbox
    -0.07
     supone
    -0.07
     Secretariat
    -0.07
    */↵↵
    -0.07
    POSITIVE LOGITS
     الجميع
    0.10
     тщательно
    0.09
     relentlessly
    0.09
     vivement
    0.08
     vigorously
    0.08
    teros
    0.08
     гер
    0.08
     thoroughly
    0.08
     Bea
    0.08
     radiant
    0.08
    Activations Density 0.011%

    No Known Activations