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

    Neuronpedia

    Jacobian LensNEW
    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. 63329
    Prev
    Next
    INDEX
    Explanations

    code snippets and tables

    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
    .Filters
    -0.08
    .notifications
    -0.07
    Cmp
    -0.07
     материалов
    -0.07
    .Invalid
    -0.07
    .await
    -0.07
     therapies
    -0.07
    دمة
    -0.07
    _cmp
    -0.07
     sims
    -0.07
    POSITIVE LOGITS
    เงิน
    0.09
     votes
    0.09
     cuant
    0.09
     vote
    0.09
     वोट
    0.09
    金额
    0.08
     vot
    0.08
    weight
    0.08
     proje
    0.08
    رقام
    0.08
    Activations Density 0.023%

    No Known Activations