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

    Neuronpedia

    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. 75866
    Prev
    Next
    INDEX
    Explanations

    wood, bark

    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
     fictional
    -0.08
    invent
    -0.08
     héros
    -0.08
     protagonistas
    -0.08
     страницы
    -0.07
     даты
    -0.07
    .That
    -0.07
     portavoz
    -0.07
     guarding
    -0.07
     challenged
    -0.07
    POSITIVE LOGITS
     biodegradable
    0.09
     kook
    0.08
     mulch
    0.08
    柏
    0.08
    Miner
    0.08
     vinegar
    0.08
     برگ
    0.08
     pellets
    0.08
    avian
    0.08
     materialen
    0.08
    Activations Density 0.006%

    No Known Activations