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. 44975
    Prev
    Next
    INDEX
    Explanations

    OK

    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
     masz
    -0.09
     Chinatown
    -0.08
     Mediterranean
    -0.08
     scrub
    -0.08
    �
    -0.07
     flea
    -0.07
     ECG
    -0.07
     Imagine
    -0.07
     Holocaust
    -0.07
     cooking
    -0.07
    POSITIVE LOGITS
     KPI
    0.10
    Driven
    0.09
    绩
    0.09
    Setter
    0.08
    推进
    0.08
     가치
    0.08
    Genes
    0.08
    Goals
    0.08
    Global
    0.08
    績
    0.08
    Activations Density 0.001%

    No Known Activations