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. 12104
    Prev
    Next
    INDEX
    Explanations

    forecast

    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
     Reflex
    -0.09
     رابط
    -0.09
     infelizmente
    -0.08
    ointer
    -0.08
     waived
    -0.08
    launcher
    -0.08
     reflex
    -0.08
     מהר
    -0.08
     réflex
    -0.08
    ner
    -0.08
    POSITIVE LOGITS
     forecasting
    0.19
     forecasts
    0.17
    Forecast
    0.17
     forecast
    0.16
     Forecast
    0.16
     прогноз
    0.15
    forecast
    0.14
     estimates
    0.14
     estim
    0.13
    估
    0.13
    Activations Density 0.020%

    No Known Activations