© 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. 30246
    Prev
    Next
    INDEX
    Explanations

    plural

    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
    كرة
    -0.08
    .birth
    -0.08
     fus
    -0.08
     inciso
    -0.08
     tighter
    -0.07
     Microwave
    -0.07
    ímp
    -0.07
     Mathemat
    -0.07
     Horton
    -0.07
     Є
    -0.07
    POSITIVE LOGITS
     refers
    0.09
     plainly
    0.08
    ള്ളി
    0.08
     سالن
    0.08
    oured
    0.08
     רח
    0.07
     നെ
    0.07
     экземпля
    0.07
    Horiz
    0.07
    oned
    0.07
    Activations Density 0.002%

    No Known Activations