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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 110488
    Prev
    Next
    INDEX
    Explanations

    checkerboard

    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
     disclosures
    -0.08
     மூ
    -0.07
    -0.07
     기관
    -0.07
     empower
    -0.07
     unemployed
    -0.07
    paged
    -0.07
     מכ
    -0.07
     필요
    -0.07
     y
    -0.07
    POSITIVE LOGITS
    patterns
    0.09
     Quilt
    0.08
    registre
    0.08
    omial
    0.08
     раду
    0.08
    _patterns
    0.08
     alternating
    0.08
     drizzle
    0.08
     blades
    0.08
     Patterns
    0.08
    Activations Density 0.003%
    No Known Activations