© 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. 45216
    Prev
    Next
    INDEX
    Explanations

    G

    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
     EXISTS
    -0.09
    .h
    -0.08
     distilled
    -0.07
    -present
    -0.07
    CY
    -0.07
    PROM
    -0.07
     PROM
    -0.07
     H
    -0.07
     FOR
    -0.07
    Present
    -0.07
    POSITIVE LOGITS
     بحر
    0.09
     حر
    0.08
     البرو
    0.08
     beträ
    0.08
     состава
    0.08
     أمير
    0.08
    이라는
    0.08
     UHD
    0.08
     hardcore
    0.08
     подряд
    0.08
    Activations Density 0.000%

    No Known Activations