© 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. 30835
    Prev
    Next
    INDEX
    Explanations

    Power

    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
    trait
    -0.08
    inform
    -0.08
    Trait
    -0.08
    人物
    -0.08
    字符
    -0.08
     chromat
    -0.08
     trait
    -0.08
    unod
    -0.08
     atores
    -0.07
    Actor
    -0.07
    POSITIVE LOGITS
     domést
    0.10
    家庭
    0.09
     solar
    0.09
     appliances
    0.09
     घरेल
    0.09
     לבית
    0.09
    घर
    0.09
     домашних
    0.09
     домаш
    0.09
     Wordpress
    0.08
    Activations Density 0.008%

    No Known Activations