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. 78551
    Prev
    Next
    INDEX
    Explanations

    inequalities

    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
    roles
    -0.07
    끄
    -0.07
    OPLE
    -0.07
    ஜ
    -0.07
     Até
    -0.07
    ുസ
    -0.07
    sol
    -0.07
     Bennett
    -0.07
     estimating
    -0.07
     relig
    -0.07
    POSITIVE LOGITS
     footh
    0.10
     besides
    0.09
     alguno
    0.09
     хоть
    0.09
     присутств
    0.08
     algún
    0.08
     среди
    0.08
     хотя
    0.08
    突破
    0.08
     mavjud
    0.08
    Activations Density 0.054%

    No Known Activations