© 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. 45442
    Prev
    Next
    INDEX
    Explanations

    favorite, favourites, favored

    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
     baze
    -0.08
    ající
    -0.08
     onchange
    -0.08
    anez
    -0.08
    ándo
    -0.07
    �영
    -0.07
     Fehler
    -0.07
    onics
    -0.07
     त्र
    -0.07
    امين
    -0.07
    POSITIVE LOGITS
     рейтинг
    0.13
     рейтин
    0.12
     favorit
    0.11
     preseason
    0.11
     predicts
    0.11
     contenders
    0.10
     challenger
    0.10
     прогноз
    0.10
     forecasts
    0.10
     מראש
    0.10
    Activations Density 0.055%

    No Known Activations