© 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. 7-RESID-POST-AA
    11. 1346
    Prev
    Next
    INDEX
    Explanations

    reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quir
    -0.08
     национ
    -0.08
    തിര
    -0.08
     omin
    -0.07
     ان
    -0.07
     Ի
    -0.07
     പിന്ത
    -0.07
    声
    -0.07
    �
    -0.07
    manı
    -0.07
    POSITIVE LOGITS
     yani
    0.08
     uter
    0.07
    (one
    0.07
     insect
    0.07
     ste
    0.07
     Shepherd
    0.07
     unk
    0.07
    Accessory
    0.07
     perfect
    0.07
    _ONE
    0.07
    Activations Density 0.000%

    No Known Activations