© 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 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. 69389
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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
     picturesque
    -0.08
     threats
    -0.08
     population
    -0.07
     foliage
    -0.07
     exits
    -0.07
     touristique
    -0.07
     Bauer
    -0.07
     vre
    -0.07
    Resident
    -0.07
     كامل
    -0.07
    POSITIVE LOGITS
     Initial
    0.10
     Inicial
    0.08
    _initial
    0.08
     цент
    0.08
     Taste
    0.08
     začet
    0.08
     ""↵
    0.08
     ""↵↵
    0.08
     ആരംഭ
    0.08
     бастап
    0.08
    Activations Density 0.050%

    No Known Activations