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. 77295
    Prev
    Next
    INDEX
    Explanations

    brain stimulation, neurological conditions

    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
     sauces
    -0.09
     belongings
    -0.08
     sauce
    -0.08
     liabilities
    -0.08
    比例
    -0.08
     �
    -0.08
    展开
    -0.08
    泄
    -0.07
    同比
    -0.07
     shirk
    -0.07
    POSITIVE LOGITS
     therapy
    0.11
     stimulation
    0.11
     хирург
    0.11
     терап
    0.11
     terapia
    0.10
     therapeutic
    0.10
     electrodes
    0.10
     العلاج
    0.10
     электр
    0.10
     stimulating
    0.10
    Activations Density 0.007%

    No Known Activations