© 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 EvalsExportsinterp-engineNEWAPI 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. 63212
    Prev
    Next
    INDEX
    Explanations

    warhammer

    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
     bao
    -0.08
    มา
    -0.08
    -best
    -0.08
     baja
    -0.08
    -del
    -0.07
     confisc
    -0.07
     stejně
    -0.07
    Bao
    -0.07
     Bao
    -0.07
    deposit
    -0.07
    POSITIVE LOGITS
    .fr
    0.08
     ദുര
    0.08
    Chess
    0.08
     amateur
    0.08
     Domino
    0.08
     др
    0.08
     احتم
    0.07
     ഗോ
    0.07
     Chess
    0.07
     manuals
    0.07
    Activations Density 0.002%

    No Known Activations