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. 58805
    Prev
    Next
    INDEX
    Explanations

    Leibniz and Calculus

    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
     desn
    -0.08
     القر
    -0.08
     averaged
    -0.08
     geren
    -0.07
     sred
    -0.07
     elliptical
    -0.07
     rojo
    -0.07
     ఖ
    -0.07
     билим
    -0.07
    蓝
    -0.07
    POSITIVE LOGITS
     touchdowns
    0.08
    .spi
    0.08
    /ns
    0.08
     combustible
    0.08
    _unicode
    0.08
     clog
    0.07
     NSF
    0.07
    Notation
    0.07
     entèn
    0.07
     Geschäft
    0.07
    Activations Density 0.001%

    No Known Activations