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. 76412
    Prev
    Next
    INDEX
    Explanations

    understanding

    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
     frequent
    -0.08
    帯
    -0.08
     bride
    -0.07
     chir
    -0.07
     wants
    -0.07
     дизайн
    -0.07
    Caret
    -0.07
     envis
    -0.07
     مالی
    -0.07
     cảnh
    -0.07
    POSITIVE LOGITS
     comprensión
    0.12
    理解
    0.11
     compreensão
    0.10
     compréhension
    0.10
    bildung
    0.10
     approfond
    0.09
     Verständnis
    0.09
     deepen
    0.09
     verdie
    0.09
     이해
    0.09
    Activations Density 0.018%

    No Known Activations