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. 58785
    Prev
    Next
    INDEX
    Explanations

    period token

    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
    یری
    -0.08
     Rial
    -0.08
    fér
    -0.08
     Φ
    -0.07
    ’n
    -0.07
    ention
    -0.07
    ilà
    -0.07
    并
    -0.07
    源码
    -0.07
     remodeling
    -0.07
    POSITIVE LOGITS
     numbered
    0.09
     ذكر
    0.08
    =cut
    0.08
     denotes
    0.08
     компани
    0.08
    maker
    0.08
    Weak
    0.08
     хто
    0.07
     thinkers
    0.07
    /:
    0.07
    Activations Density 0.003%

    No Known Activations