© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 31497
    Prev
    Next
    INDEX
    Explanations

    most/many

    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
     extrap
    -0.08
    bla
    -0.08
     sizes
    -0.08
     amp
    -0.07
     levering
    -0.07
     thus
    -0.07
     furnished
    -0.07
    ienda
    -0.07
    esian
    -0.07
    ування
    -0.07
    POSITIVE LOGITS
     lidí
    0.09
     män
    0.09
    	Game
    0.09
     Readers
    0.09
     Articles
    0.09
    players
    0.09
     Officers
    0.09
    ordinary
    0.08
     людей
    0.08
     Ordinary
    0.08
    Activations Density 0.017%

    No Known Activations