© 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. 45577
    Prev
    Next
    INDEX
    Explanations

    <meta

    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
    या
    -0.07
     feu
    -0.07
    (filter
    -0.07
     SPD
    -0.07
     Pascal
    -0.07
     pickups
    -0.07
     convertir
    -0.07
    110
    -0.07
    下注
    -0.07
     quatre
    -0.07
    POSITIVE LOGITS
     título
    0.09
    .title
    0.09
    Título
    0.09
     title
    0.08
     titulo
    0.08
    title
    0.08
    Sr
    0.08
     название
    0.08
     тұ
    0.07
     проекта
    0.07
    Activations Density 0.002%

    No Known Activations