© 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 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. 69516
    Prev
    Next
    INDEX
    Explanations

    start of quote

    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
    ిస్త
    -0.08
    দের
    -0.08
    -uns
    -0.08
     Ald
    -0.08
     bald
    -0.07
     cond
    -0.07
    yay
    -0.07
    -proof
    -0.07
     बनाए
    -0.07
     Indonesian
    -0.07
    POSITIVE LOGITS
    拿大
    0.09
    've
    0.08
    ANDARD
    0.07
    cluded
    0.07
    어서
    0.07
     �
    0.07
    'll
    0.07
    어요
    0.07
    're
    0.07
     Rh
    0.07
    Activations Density 0.071%

    No Known Activations