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. 65887
    Prev
    Next
    INDEX
    Explanations

    financial planning, forecasting

    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
     ож
    -0.08
     bagian
    -0.08
     위치
    -0.07
     velocidades
    -0.07
     alunos
    -0.07
     notebook
    -0.07
    Elegant
    -0.07
    _socket
    -0.07
     سرعة
    -0.07
    otine
    -0.07
    POSITIVE LOGITS
     Ahead
    0.16
     ahead
    0.15
    Ahead
    0.15
    ahead
    0.14
     horizonte
    0.14
     horizons
    0.14
     futuro
    0.13
    Forecast
    0.13
     vooruit
    0.13
     horizon
    0.13
    Activations Density 0.022%

    No Known Activations