© 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. 11-RESID-POST-AA
    11. 113518
    Prev
    Next
    INDEX
    Explanations

    borders

    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
     reels
    -0.09
    ème
    -0.08
     minutos
    -0.08
    -ticket
    -0.08
     Zeitpunkt
    -0.07
    -ton
    -0.07
    /forms
    -0.07
     தய
    -0.07
     FOLLOW
    -0.07
     minuti
    -0.07
    POSITIVE LOGITS
     east
    0.10
    邻
    0.09
     bordered
    0.09
     bordering
    0.09
     भू
    0.09
    ियां
    0.08
     matières
    0.08
    ignty
    0.08
    _neighbors
    0.08
     seng
    0.08
    Activations Density 0.015%

    No Known Activations