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. 24073
    Prev
    Next
    INDEX
    Explanations

    of

    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
     인정
    -0.07
     discern
    -0.07
     {}\
    -0.07
     misst
    -0.07
     Klick
    -0.07
    остью
    -0.07
     [(
    -0.07
     [{}
    -0.07
     `[
    -0.07
     pressured
    -0.07
    POSITIVE LOGITS
     ciò
    0.09
     drawings
    0.09
     lush
    0.09
    摄影
    0.08
     flora
    0.08
     ಹಿನ್ನೆ
    0.08
    styles
    0.08
    _environment
    0.08
     Photograph
    0.08
     പശ
    0.08
    Activations Density 0.006%

    No Known Activations