© 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. 71219
    Prev
    Next
    INDEX
    Explanations

    chemistry/cellular processes

    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
     Southeast
    -0.08
     camouflage
    -0.08
     spotted
    -0.07
    ढ
    -0.07
    (cnt
    -0.07
     cnt
    -0.07
    нок
    -0.07
     convex
    -0.07
     recognized
    -0.07
     convection
    -0.07
    POSITIVE LOGITS
     المياه
    0.09
     पानी
    0.08
     kin
    0.08
     bière
    0.08
    venta
    0.08
     Viktor
    0.08
     þú
    0.08
     бў
    0.08
     ulan
    0.08
    .Root
    0.08
    Activations Density 0.000%

    No Known Activations