© 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. 63920
    Prev
    Next
    INDEX
    Explanations

    vanity metrics

    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
     plateau
    -0.07
     vert
    -0.07
     Ident
    -0.07
    (bg
    -0.07
     মাঝে
    -0.07
    've
    -0.07
    lego
    -0.07
    heng
    -0.07
     retro
    -0.07
    ming
    -0.07
    POSITIVE LOGITS
     vanity
    0.10
    itty
    0.09
     космет
    0.09
     ornamental
    0.08
     cosmet
    0.08
     cosmetic
    0.08
     AREA
    0.08
    �
    0.07
     Candida
    0.07
     MATR
    0.07
    Activations Density 0.002%

    No Known Activations