Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 90099
    Prev
    Next
    INDEX
    Explanations

    thread

    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
     तेल
    -0.09
     oil
    -0.08
     jerseys
    -0.08
    829
    -0.08
     gegründet
    -0.08
    足球
    -0.08
     glaciers
    -0.08
     jersey
    -0.08
    memcmp
    -0.07
     कप
    -0.07
    POSITIVE LOGITS
     René
    0.08
     improvement
    0.08
     melhorias
    0.08
     Ruff
    0.08
    Shortcut
    0.08
     સુધ
    0.07
     improvements
    0.07
    Cult
    0.07
    (serial
    0.07
    IPS
    0.07
    Activations Density 0.003%

    No Known Activations