© 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. 70564
    Prev
    Next
    INDEX
    Explanations

    Definitions in legal agreements

    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
    积极
    -0.08
    hift
    -0.08
    网址
    -0.08
     Wein
    -0.08
    销量
    -0.08
    .baidu
    -0.08
    销售
    -0.07
    广州
    -0.07
     minimale
    -0.07
    itudine
    -0.07
    POSITIVE LOGITS
     Loose
    0.08
     loose
    0.08
    ским
    0.08
    (with
    0.08
     tuot
    0.07
     throughout
    0.07
    cron
    0.07
    Executed
    0.07
    chron
    0.07
    -inflammatory
    0.07
    Activations Density 0.001%

    No Known Activations