© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 99569
    Prev
    Next
    INDEX
    Explanations

    Game Power-ups and mechanics

    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
     Salisbury
    -0.09
     лоз
    -0.08
     documenting
    -0.08
    აცი
    -0.08
    იბ
    -0.08
     cuidadosamente
    -0.08
     senators
    -0.08
     prescribing
    -0.08
    орус
    -0.08
     conservative
    -0.08
    POSITIVE LOGITS
     क्षमता
    0.09
     बेहतर
    0.09
     collectibles
    0.09
    Speed
    0.08
     speed
    0.08
     सक्षम
    0.08
    _SPEED
    0.08
     Cap
    0.08
     amélior
    0.08
     Speed
    0.08
    Activations Density 0.014%

    No Known Activations