© 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. 3-RESID-POST-AA
    11. 1205
    Prev
    Next
    INDEX
    Explanations

    effect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gover
    -0.08
    报价
    -0.08
    (Client
    -0.07
    Lig
    -0.07
    bp
    -0.07
     twig
    -0.07
     presented
    -0.07
    Sara
    -0.07
    废
    -0.07
     تك
    -0.07
    POSITIVE LOGITS
     Raphael
    0.07
    mur
    0.07
     Rocks
    0.07
     Bod
    0.07
    ij
    0.07
     ਕ
    0.07
    റ
    0.07
    仕様
    0.07
     nghi
    0.07
     ni
    0.07
    Activations Density 0.008%

    No Known Activations