© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 97426
    Prev
    Next
    INDEX
    Explanations

    Math and code context

    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
     rogue
    -0.08
     Oyster
    -0.07
     ಮೇ
    -0.07
     keinen
    -0.07
     Factory
    -0.07
     Metallic
    -0.07
    ಷ್ಟ
    -0.07
    ベ
    -0.07
    וש
    -0.07
     Web
    -0.07
    POSITIVE LOGITS
    umut
    0.09
    u
    0.08
    REAT
    0.08
    ang
    0.08
    yl
    0.08
    ylim
    0.08
    ੰਗ
    0.08
    Y
    0.07
    ਾਇ
    0.07
    Gee
    0.07
    Activations Density 0.014%

    No Known Activations