© 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. 71041
    Prev
    Next
    INDEX
    Explanations

    halo reach

    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
     caráter
    -0.08
     proverbial
    -0.07
    .Pe
    -0.07
     המח
    -0.07
     legado
    -0.07
    oum
    -0.07
    uplic
    -0.07
     Preconditions
    -0.07
     Faculty
    -0.07
     faculty
    -0.07
    POSITIVE LOGITS
     çı
    0.08
     Dragons
    0.08
     Cowboy
    0.08
     beings
    0.08
     dragons
    0.08
     dwarf
    0.07
     spaces
    0.07
     astronauts
    0.07
     हे
    0.07
     agencias
    0.07
    Activations Density 0.003%

    No Known Activations