© 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. 110
    Prev
    Next
    INDEX
    Explanations

    the

    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
    <Date
    -0.08
     aspir
    -0.07
    DATE
    -0.07
    <|reserved_200016|>
    -0.07
    (dialog
    -0.07
    731
    -0.07
    UP
    -0.07
     customized
    -0.07
    <|endoftext|>
    -0.07
    الت
    -0.07
    POSITIVE LOGITS
    område
    0.09
     område
    0.08
     cumul
    0.08
     surcharge
    0.08
     offenders
    0.08
     facteur
    0.08
    指数
    0.08
    stek
    0.08
    -warning
    0.08
     incompet
    0.08
    Activations Density 0.002%

    No Known Activations