© 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. 6275
    Prev
    Next
    INDEX
    Explanations

    Math and foreign languages

    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
    alne
    -0.09
    لا
    -0.08
    amaa
    -0.07
    .items
    -0.07
     repar
    -0.07
     клуб
    -0.07
     XE
    -0.07
    icias
    -0.07
     repart
    -0.07
     curso
    -0.07
    POSITIVE LOGITS
     tehnolog
    0.08
    җ
    0.07
    uddy
    0.07
     sizzling
    0.07
     Dash
    0.07
    ђ
    0.07
     Milliarden
    0.07
    umenten
    0.07
    anha
    0.07
     shimmering
    0.07
    Activations Density 0.013%

    No Known Activations