© 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. 11-RESID-POST-AA
    11. 95160
    Prev
    Next
    INDEX
    Explanations

    code and mathematics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ups
    -0.08
    CString
    -0.08
    (print
    -0.08
     ஊ
    -0.08
     الإ
    -0.08
    ATM
    -0.08
    紙
    -0.07
     barrage
    -0.07
    wur
    -0.07
    -0.07
    POSITIVE LOGITS
     inox
    0.08
    β
    0.08
     compar
    0.08
     Lisa
    0.07
    xiom
    0.07
     β
    0.07
     തീയ
    0.07
    _batch
    0.07
     양
    0.07
     ro
    0.07
    Activations Density 0.119%
    No Known Activations