© 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. 3-RESID-POST-AA
    11. 2532
    Prev
    Next
    INDEX
    Explanations

    大

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     கட
    -0.08
    emap
    -0.08
    avier
    -0.08
    older
    -0.08
     Fifty
    -0.07
    osest
    -0.07
     இல
    -0.07
     �
    -0.07
     végét
    -0.07
     விழ
    -0.07
    POSITIVE LOGITS
    做好
    0.08
    我国
    0.08
     эффективность
    0.07
    提高
    0.07
    值得
    0.07
    Federal
    0.07
     sep
    0.07
    А
    0.07
    º
    0.07
    ક્ટ
    0.07
    Activations Density 0.002%

    No Known Activations