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. 112234
    Prev
    Next
    INDEX
    Explanations

    hot springs

    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
    vias
    -0.08
     Curriculum
    -0.08
    ɔn
    -0.07
     Código
    -0.07
     INTRO
    -0.07
    .items
    -0.07
     Woj
    -0.07
    .Control
    -0.07
     작성
    -0.07
    _events
    -0.07
    POSITIVE LOGITS
     jacuzzi
    0.13
     baths
    0.13
     soaking
    0.12
     spa
    0.12
    按摩
    0.12
     soothe
    0.11
     thermal
    0.10
     Thermal
    0.10
    浴
    0.10
     soak
    0.10
    Activations Density 0.021%

    No Known Activations