© 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. 91389
    Prev
    Next
    INDEX
    Explanations

    ed

    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
     sua
    -0.09
    	de
    -0.08
    ที่
    -0.08
    Gay
    -0.07
    ซี
    -0.07
    (sample
    -0.07
     облад
    -0.07
     guy
    -0.07
     dichter
    -0.07
    еген
    -0.07
    POSITIVE LOGITS
     Twitter
    0.09
     新闻
    0.08
     গত
    0.08
     Curriculum
    0.08
     PRODUCT
    0.08
     Risiko
    0.08
    新闻
    0.07
    ynamo
    0.07
    _resource
    0.07
     Workplace
    0.07
    Activations Density 0.017%

    No Known Activations