© 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. 70481
    Prev
    Next
    INDEX
    Explanations

    time

    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
    ira
    -0.07
    _DROP
    -0.07
    بوط
    -0.07
     interdit
    -0.07
     artifacts
    -0.07
     ين
    -0.07
     avan
    -0.07
     lea
    -0.07
     drone
    -0.07
     notch
    -0.06
    POSITIVE LOGITS
     سنوات
    0.10
    months
    0.09
     месяцев
    0.09
     weeks
    0.09
     дней
    0.09
     lich
    0.09
    Years
    0.09
    weeks
    0.09
    years
    0.09
     liters
    0.09
    Activations Density 0.007%

    No Known Activations