© 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. 111151
    Prev
    Next
    INDEX
    Explanations

    Field of vision

    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
    رة
    -0.08
    FXML
    -0.08
     Cutter
    -0.07
    WEB
    -0.07
    *cos
    -0.07
    .central
    -0.07
     signif
    -0.07
     Lon
    -0.07
     Scenic
    -0.07
    一下
    -0.07
    POSITIVE LOGITS
     granted
    0.08
    _sup
    0.08
    ikkel
    0.08
     resolución
    0.08
    yez
    0.08
    sup
    0.07
     calendar
    0.07
    ynet
    0.07
     uppl
    0.07
    chts
    0.07
    Activations Density 0.001%

    No Known Activations