Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 48994
    Prev
    Next
    INDEX
    Explanations

    psychology

    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
    .gl
    -0.08
     Aircraft
    -0.08
     exaggerated
    -0.08
     tím
    -0.07
     aircraft
    -0.07
     Radi
    -0.07
     लाइन
    -0.07
     unidentified
    -0.07
     lying
    -0.07
    ലൈ
    -0.07
    POSITIVE LOGITS
     psychologist
    0.09
     textbooks
    0.08
    psych
    0.08
    兼职
    0.08
    forum
    0.08
     gait
    0.08
     psychologists
    0.07
    0.07
    心理
    0.07
    出版
    0.07
    Activations Density 0.010%

    No Known Activations