© 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. 70784
    Prev
    Next
    INDEX
    Explanations

    multilingual texts

    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
    acchar
    -0.08
    okuq
    -0.07
    _SQL
    -0.07
     pamwe
    -0.07
    ù
    -0.07
     kesin
    -0.07
    ffiti
    -0.07
     Soul
    -0.07
    oría
    -0.07
     pressures
    -0.07
    POSITIVE LOGITS
     субъ
    0.08
     болсон
    0.08
     tsoa
    0.08
     weyn
    0.08
     Rhein
    0.07
     five
    0.07
    .grp
    0.07
     있기
    0.07
     بڻ
    0.07
     نشده
    0.07
    Activations Density 0.000%

    No Known Activations