© 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. 30832
    Prev
    Next
    INDEX
    Explanations

    chord

    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
    જી
    -0.09
     Dish
    -0.09
    _recipe
    -0.08
     Physi
    -0.08
    ↵↵↵↵↵↵
    -0.08
    Dish
    -0.07
    صفات
    -0.07
    (recipe
    -0.07
     overs
    -0.07
     Fringe
    -0.07
    POSITIVE LOGITS
     قطع
    0.08
    eraar
    0.08
     taut
    0.08
     �
    0.07
     concluding
    0.07
    [href
    0.07
    ibling
    0.07
     enclosed
    0.07
     исп
    0.07
     conclude
    0.07
    Activations Density 0.013%

    No Known Activations