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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 60640
    Prev
    Next
    INDEX
    Explanations

    favor

    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
     Q
    -0.08
     어떤
    -0.07
     ep
    -0.07
     costo
    -0.07
     finance
    -0.07
     Али
    -0.07
     bonds
    -0.07
     skuld
    -0.07
     архит
    -0.07
    äder
    -0.07
    POSITIVE LOGITS
     부탁
    0.13
    お願い
    0.13
     Bitte
    0.13
    お願
    0.12
     PLEASE
    0.12
     kindly
    0.12
    please
    0.12
    Bitte
    0.11
    勿
    0.11
     прось
    0.11
    Activations Density 0.088%

    No Known Activations