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. 90151
    Prev
    Next
    INDEX
    Explanations

    anatomy

    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
    投入
    -0.11
     optimism
    -0.10
     volatility
    -0.10
     indie
    -0.09
     ideological
    -0.09
     lemonade
    -0.09
     sandbox
    -0.09
     ration
    -0.09
     incremental
    -0.09
     polling
    -0.09
    POSITIVE LOGITS
     anatom
    0.18
     anatomical
    0.17
     anatomy
    0.15
     Anatom
    0.15
    Anterior
    0.12
     dorsal
    0.12
     cartilage
    0.12
     Anatomy
    0.12
     anat
    0.12
     mandib
    0.12
    Activations Density 0.029%

    No Known Activations