© 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. 110210
    Prev
    Next
    INDEX
    Explanations

    Sponsorships and naming rights

    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
    jejer
    -0.08
    uales
    -0.08
     higit
    -0.08
    ्यवाद
    -0.08
    ystem
    -0.08
    jul
    -0.08
    !=(
    -0.08
    incipal
    -0.07
    ujących
    -0.07
     man's
    -0.07
    POSITIVE LOGITS
    Named
    0.10
     naming
    0.10
     Named
    0.10
     Naming
    0.10
     nombr
    0.09
     named
    0.09
    named
    0.09
    Naming
    0.09
    .Named
    0.09
    .named
    0.08
    Activations Density 0.025%

    No Known Activations