© 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. 23-RESID-POST-AA
    11. 50280
    Prev
    Next
    INDEX
    Explanations

    Sports scores and wins

    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
    输了
    -0.11
     competed
    -0.11
     losing
    -0.11
     Gewinner
    -0.11
     Winning
    -0.11
    Winning
    -0.11
     losers
    -0.11
     disputar
    -0.10
    中奖
    -0.10
     competición
    -0.10
    POSITIVE LOGITS
     convinc
    0.11
     esmag
    0.10
     routing
    0.10
     comfortable
    0.10
     emph
    0.10
     pohod
    0.10
     thriller
    0.10
     comfortably
    0.10
    routing
    0.10
     Routing
    0.09
    Activations Density 0.021%

    No Known Activations