© 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. 94792
    Prev
    Next
    INDEX
    Explanations

    possibility

    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
     letterlijk
    -0.08
     brisk
    -0.08
    假
    -0.08
    arthy
    -0.08
     literally
    -0.07
    desk
    -0.07
     wasn
    -0.07
     anonymously
    -0.07
    િક
    -0.07
    tym
    -0.07
    POSITIVE LOGITS
     restrictions
    0.09
     constraints
    0.09
     factors
    0.09
     imposed
    0.08
     causing
    0.08
     curvature
    0.08
     forcing
    0.08
     тарт
    0.08
     specifics
    0.08
     правила
    0.07
    Activations Density 0.058%

    No Known Activations