© 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. 64533
    Prev
    Next
    INDEX
    Explanations

    Star Wars prequels

    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
     alimentation
    -0.08
     expectancy
    -0.08
     hospitality
    -0.08
     установка
    -0.08
    (property
    -0.08
     خواه
    -0.08
     direction
    -0.08
    efu
    -0.08
     grundleg
    -0.07
     liste
    -0.07
    POSITIVE LOGITS
     degeneration
    0.08
     acne
    0.08
    .Visible
    0.08
     канц
    0.08
     apopt
    0.08
    -ip
    0.08
     apoptosis
    0.08
     incompet
    0.08
     അധിക
    0.07
    .Generate
    0.07
    Activations Density 0.003%

    No Known Activations