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. 11747
    Prev
    Next
    INDEX
    Explanations

    optimistic

    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
    ällt
    -0.07
     Spill
    -0.07
    当天
    -0.07
     Ciid
    -0.07
     Clock
    -0.07
     exteriores
    -0.07
    -"
    -0.07
    -Light
    -0.07
     Concepts
    -0.07
     العودة
    -0.07
    POSITIVE LOGITS
    _HTTP
    0.08
     oph
    0.08
     abortion
    0.08
    YP
    0.07
    ेय
    0.07
     biting
    0.07
     abs
    0.07
     delect
    0.07
     anemia
    0.07
     acet
    0.07
    Activations Density 0.000%

    No Known Activations