© 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. 48453
    Prev
    Next
    INDEX
    Explanations

    109

    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
    יסוי
    -0.08
     マ
    -0.08
    _UPLOAD
    -0.08
    Gill
    -0.07
    Mel
    -0.07
     Melbourne
    -0.07
     Mueller
    -0.07
     cul
    -0.07
     resolver
    -0.07
     mety
    -0.07
    POSITIVE LOGITS
    enka
    0.08
     таким
    0.08
     площад
    0.07
    _region
    0.07
    ubern
    0.07
     deformation
    0.07
     ร
    0.07
    .Н
    0.07
     منها
    0.07
     بط
    0.07
    Activations Density 0.000%

    No Known Activations