© 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. 71112
    Prev
    Next
    INDEX
    Explanations

    deploy

    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
     перес
    -0.08
     pursuits
    -0.07
    ข้อง
    -0.07
     Kirst
    -0.07
    BU
    -0.07
     पता
    -0.07
     excursions
    -0.07
     контроль
    -0.07
     KS
    -0.07
     determining
    -0.07
    POSITIVE LOGITS
    મેન્ટ
    0.09
     دیا
    0.08
     tactics
    0.08
     dort
    0.08
    .cms
    0.08
     Dar
    0.08
    eteer
    0.07
     Bab
    0.07
    :flex
    0.07
    Filters
    0.07
    Activations Density 0.009%

    No Known Activations