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. 42083
    Prev
    Next
    INDEX
    Explanations

    vaccine

    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
    elong
    -0.08
    ordo
    -0.07
    ახ
    -0.07
     etched
    -0.07
    위
    -0.07
     bracket
    -0.07
    柱
    -0.07
     shallow
    -0.07
    ße
    -0.07
    wards
    -0.06
    POSITIVE LOGITS
     cons
    0.08
    潮
    0.08
     miracle
    0.08
     종류
    0.08
     Andrade
    0.08
     Tren
    0.08
     Panasonic
    0.07
     makers
    0.07
     workforce
    0.07
     auprès
    0.07
    Activations Density 0.005%

    No Known Activations