© 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. 48159
    Prev
    Next
    INDEX
    Explanations

    ""

    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
    vie
    -0.07
     sagitt
    -0.07
     siy
    -0.07
     ár
    -0.07
     koy
    -0.07
    iy
    -0.07
    -0.07
     flushing
    -0.07
    /internal
    -0.07
    Signup
    -0.07
    POSITIVE LOGITS
    rings
    0.08
    heast
    0.08
    uleke
    0.08
    zne
    0.07
     rings
    0.07
    drá
    0.07
    ര
    0.07
     TRUST
    0.07
    wenza
    0.07
    level
    0.07
    Activations Density 0.000%
    No Known Activations