© 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. 23-RESID-POST-AA
    11. 49612
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SECRET
    -0.08
     Rupert
    -0.08
     Entwicklung
    -0.08
    ارضة
    -0.07
    Sto
    -0.07
     gratuits
    -0.07
     explaining
    -0.07
    Shake
    -0.07
     конструкции
    -0.07
    endab
    -0.07
    POSITIVE LOGITS
    ÿ
    0.09
     ydy
    0.09
    stäl
    0.08
     Ym
    0.08
    ­↵↵
    0.07
    gt
    0.07
    .ones
    0.07
     ym
    0.07
    ली
    0.07
     YYYY
    0.07
    Activations Density 0.000%

    No Known Activations