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. 88196
    Prev
    Next
    INDEX
    Explanations

    、

    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
     Macron
    -0.08
    ometer
    -0.08
    斤
    -0.08
     inches
    -0.08
    互
    -0.08
    左右
    -0.08
    Exif
    -0.08
     RGB
    -0.07
     ten
    -0.07
     entgegen
    -0.07
    POSITIVE LOGITS
     cấu
    0.08
     મુલાકાત
    0.08
    prio
    0.08
    遗漏
    0.08
    šn
    0.08
    Ontology
    0.08
    (crate
    0.08
     ontology
    0.08
     संक्रमण
    0.07
     honesty
    0.07
    Activations Density 0.002%

    No Known Activations