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. 44132
    Prev
    Next
    INDEX
    Explanations

    Excel/VBA formulas

    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
     hul
    -0.07
     artery
    -0.07
     predecessors
    -0.07
     Guillaume
    -0.07
    itzer
    -0.07
     dominating
    -0.07
    aisesti
    -0.07
     وعلى
    -0.07
     Chile
    -0.07
    ്യമ
    -0.07
    POSITIVE LOGITS
     വരെ
    0.09
     abrang
    0.08
     வரை
    0.08
    Ig
    0.08
     Jusqu
    0.08
     వరకు
    0.08
     Ό
    0.08
    oscope
    0.07
     informat
    0.07
    _append
    0.07
    Activations Density 0.002%

    No Known Activations