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. 65372
    Prev
    Next
    INDEX
    Explanations

    mathematics

    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
     localhost
    -0.08
     dying
    -0.08
     emoji
    -0.08
     orally
    -0.08
    390
    -0.07
    এ
    -0.07
     trials
    -0.07
     entering
    -0.07
    ecutable
    -0.07
    -author
    -0.07
    POSITIVE LOGITS
     mathem
    0.14
     mathematical
    0.13
     mathematics
    0.13
     underpin
    0.13
    数学
    0.12
     matemática
    0.12
     matem
    0.11
     Mathematical
    0.11
     elegance
    0.11
     математ
    0.11
    Activations Density 0.021%

    No Known Activations