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. 43067
    Prev
    Next
    INDEX
    Explanations

    rehabilitation

    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
     lur
    -0.09
     bloggers
    -0.08
     Bloggers
    -0.08
     ब्लॉग
    -0.08
    博客
    -0.08
     Agoda
    -0.08
     Expedia
    -0.08
     Tencent
    -0.08
    ичные
    -0.08
     CEOs
    -0.08
    POSITIVE LOGITS
     therapy
    0.15
     therapies
    0.14
     interventions
    0.13
     therapeutic
    0.13
     terapi
    0.13
     rehabilitation
    0.13
     العلاج
    0.12
     therap
    0.12
    therapy
    0.12
     терап
    0.12
    Activations Density 0.018%

    No Known Activations