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. 54277
    Prev
    Next
    INDEX
    Explanations

    trading and investment

    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
    ried
    -0.09
     houver
    -0.08
    ITable
    -0.08
     추진
    -0.08
    inea
    -0.08
    _AUTO
    -0.08
     시행
    -0.07
    -la
    -0.07
    immä
    -0.07
    Tent
    -0.07
    POSITIVE LOGITS
     TFT
    0.09
     vard
    0.08
     दैनिक
    0.08
     dagelijkse
    0.08
     તપાસ
    0.08
     günlük
    0.07
     täglichen
    0.07
     топ
    0.07
     DAILY
    0.07
     ef
    0.07
    Activations Density 0.005%

    No Known Activations