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. 56105
    Prev
    Next
    INDEX
    Explanations

    medicine and function

    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
    _instances
    -0.08
    modell
    -0.08
    Checksum
    -0.08
    Inst
    -0.08
    池
    -0.08
     Angeb
    -0.08
    対象
    -0.08
    dang
    -0.08
    Routing
    -0.08
     Instances
    -0.08
    POSITIVE LOGITS
    生活
    0.13
     rehabilitation
    0.12
     생활
    0.11
     ജീവിത
    0.11
    생활
    0.11
     lifestyle
    0.11
     ಜೀವನ
    0.11
     زندگی
    0.10
     जीवन
    0.10
     જીવન
    0.10
    Activations Density 0.045%

    No Known Activations