© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 45756
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
     workshops
    -0.09
     Workshops
    -0.08
     wiss
    -0.08
     designation
    -0.08
     workshop
    -0.08
     outbreaks
    -0.08
     dissertations
    -0.08
     š
    -0.08
    /logout
    -0.08
     notas
    -0.08
    POSITIVE LOGITS
    ineq
    0.10
     inequality
    0.10
     convex
    0.09
     sharper
    0.09
     generosity
    0.09
     exager
    0.09
     superiority
    0.08
     inequalities
    0.08
     positivity
    0.08
     justified
    0.08
    Activations Density 0.112%

    No Known Activations