© 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. 108436
    Prev
    Next
    INDEX
    Explanations

    (sizeof

    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
     Hardcover
    -0.09
    גנ
    -0.08
     Ram
    -0.08
    难
    -0.08
     terro
    -0.08
    kompl
    -0.07
     Simpsons
    -0.07
     usine
    -0.07
     Schwier
    -0.07
     allant
    -0.07
    POSITIVE LOGITS
     размещ
    0.08
    elt
    0.08
    δευ
    0.07
     оплач
    0.07
    AND
    0.07
    _paid
    0.07
     دم
    0.07
    .tb
    0.07
    *p
    0.07
    .class
    0.07
    Activations Density 0.004%

    No Known Activations