© 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. 63290
    Prev
    Next
    INDEX
    Explanations

    Processing and handling fees

    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
    ૅ
    -0.08
    203
    -0.07
     smith
    -0.07
    .myapplication
    -0.07
    ↵//
    -0.07
    ı
    -0.07
     fur
    -0.07
    ?.
    -0.07
     hosped
    -0.07
    แ
    -0.07
    POSITIVE LOGITS
    oux
    0.09
     Melt
    0.09
     Loh
    0.09
     Talking
    0.09
    .Slf
    0.08
     Jol
    0.08
     Už
    0.08
     Prescott
    0.08
     Goog
    0.08
     Scanner
    0.08
    Activations Density 0.000%

    No Known Activations