© 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. 65370
    Prev
    Next
    INDEX
    Explanations

    and

    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
     mushroom
    -0.09
     gummy
    -0.09
     Bram
    -0.09
     slim
    -0.08
    tmpl
    -0.08
    sev
    -0.08
    weg
    -0.08
    ozy
    -0.08
    -Bahn
    -0.08
    pec
    -0.08
    POSITIVE LOGITS
    整数
    0.08
     Обычно
    0.08
     किलो
    0.08
     monot
    0.08
    ycles
    0.08
     представлены
    0.07
     pren
    0.07
     radians
    0.07
     lain
    0.07
    范围
    0.07
    Activations Density 0.017%

    No Known Activations