© 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. 51576
    Prev
    Next
    INDEX
    Explanations

    game

    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
     enacted
    -0.07
     munc
    -0.07
     aporte
    -0.07
    ựa
    -0.07
     compromet
    -0.07
    .presenter
    -0.07
     acces
    -0.07
    مخت
    -0.07
    .Proxy
    -0.07
     competed
    -0.06
    POSITIVE LOGITS
     streak
    0.27
     consecutive
    0.22
    连续
    0.22
     consecut
    0.21
    连
    0.21
     连
    0.20
    連
    0.19
     سلسلة
    0.18
     sequência
    0.18
     unbeaten
    0.17
    Activations Density 0.063%

    No Known Activations