© 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. 108701
    Prev
    Next
    INDEX
    Explanations

    kinks

    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
    kelas
    -0.09
    unar
    -0.08
    ידה
    -0.08
     rámci
    -0.08
     순
    -0.08
    범
    -0.08
    вол
    -0.08
    마
    -0.07
    หม
    -0.07
     답
    -0.07
    POSITIVE LOGITS
    明显
    0.08
     elbows
    0.08
     reduz
    0.07
     أيضًا
    0.07
     irr
    0.07
     kyl
    0.07
    әл
    0.07
     reduct
    0.07
    _vectors
    0.07
    群众
    0.07
    Activations Density 0.002%

    No Known Activations