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. 43248
    Prev
    Next
    INDEX
    Explanations

    non-English languages

    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
    न्�
    -0.09
     justified
    -0.09
    르고
    -0.08
     bottled
    -0.08
    Dom
    -0.08
     Gloria
    -0.08
     domic
    -0.08
    Heart
    -0.08
    CALE
    -0.08
     घरेल
    -0.07
    POSITIVE LOGITS
     hydrochlor
    0.08
    /co
    0.08
     constructs
    0.07
     chemistry
    0.07
     કો�
    0.07
     penalty
    0.07
     Datum
    0.07
     사항
    0.07
    idine
    0.07
    oline
    0.07
    Activations Density 0.009%

    No Known Activations