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. 15-RESID-POST-AA
    6. 19395
    Prev
    Next
    INDEX
    Explanations

    healing and repair

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Loud
    -0.10
     Tucker
    -0.09
     loud
    -0.09
     гром
    -0.09
     Pricing
    -0.09
     Philosophy
    -0.08
     Trivia
    -0.08
     eclectic
    -0.08
     calculator
    -0.08
    �
    -0.08
    POSITIVE LOGITS
     healing
    0.23
     repair
    0.21
     repairing
    0.20
    Healing
    0.20
     Healing
    0.19
     repairs
    0.18
    repair
    0.18
     heal
    0.17
     regeneration
    0.17
     heals
    0.17
    Activations Density 0.026%

    No Known Activations