© 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. 23-RESID-POST-AA
    11. 51810
    Prev
    Next
    INDEX
    Explanations

    say "the number 57"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     meen
    -0.10
     alumnes
    -0.10
     Kompetenz
    -0.09
    рест
    -0.09
     competence
    -0.09
    INCT
    -0.09
     Gardner
    -0.09
     Welch
    -0.09
     Bett
    -0.09
     المعدات
    -0.09
    POSITIVE LOGITS
    57
    0.30
    057
    0.16
    570
    0.12
    幽
    0.12
     humor
    0.11
     Siya
    0.11
     emo
    0.11
     eerie
    0.11
     humorous
    0.11
    59
    0.11
    Activations Density 0.016%

    No Known Activations