© 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. 19-RESID-POST-AA
    11. 18639
    Prev
    Next
    INDEX
    Explanations

    tennis

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    程序集
    -0.12
     soot
    -0.11
    .Compiler
    -0.11
     উপজ
    -0.11
     combustion
    -0.11
     gasoline
    -0.10
     oxygen
    -0.10
     VEH
    -0.10
     муницип
    -0.10
     BMP
    -0.10
    POSITIVE LOGITS
     tennis
    0.28
     Tennis
    0.23
     tenis
    0.23
     Wimbledon
    0.22
     Djokovic
    0.21
     badminton
    0.20
     racket
    0.19
    imbledon
    0.18
     tournament
    0.17
     Federer
    0.17
    Activations Density 0.022%

    No Known Activations