© 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. 63797
    Prev
    Next
    INDEX
    Explanations

    time and dates

    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
     наверное
    -0.07
    .cpu
    -0.07
    ）、
    -0.07
    ）》
    -0.07
     ഇന്ന
    -0.07
    ?>
    -0.07
     Landkreis
    -0.07
    ?>"
    -0.07
     周
    -0.07
    POSITIVE LOGITS
     Plateau
    0.07
    anaan
    0.07
    itiva
    0.07
     Ê
    0.07
     steady
    0.07
     deducted
    0.07
    chaine
    0.07
     supportive
    0.07
    ethi
    0.07
    endur
    0.07
    Activations Density 0.017%

    No Known Activations