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. 58327
    Prev
    Next
    INDEX
    Explanations

    as

    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
     ніж
    -0.09
     खोल
    -0.08
     Boston
    -0.08
     такі
    -0.07
     Detroit
    -0.07
     кост
    -0.07
     â
    -0.07
     goog
    -0.07
     такими
    -0.07
     define
    -0.07
    POSITIVE LOGITS
    ليق
    0.09
    ಕರ್ತ
    0.08
    PLEASE
    0.08
    anything
    0.08
    BLUE
    0.08
    Veuillez
    0.08
    UNDLE
    0.08
    GREEN
    0.08
    SIGNED
    0.08
    ounces
    0.08
    Activations Density 0.004%

    No Known Activations