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. 49745
    Prev
    Next
    INDEX
    Explanations

    Tax information

    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
     Flower
    -0.08
    _accept
    -0.08
    -lg
    -0.07
     Usually
    -0.07
    ishop
    -0.07
     Kasi
    -0.07
    Flower
    -0.07
     Accept
    -0.07
    важа
    -0.07
    ಕರ
    -0.07
    POSITIVE LOGITS
     buckle
    0.09
     нагрузки
    0.08
     frontier
    0.08
    conten
    0.08
     discip
    0.08
     disposizione
    0.08
     mostr
    0.08
     buitenland
    0.08
     суммы
    0.07
    иций
    0.07
    Activations Density 0.003%

    No Known Activations