© 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. 44396
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    unker
    -0.09
    .Skip
    -0.09
     ہوگ
    -0.09
     ہوج
    -0.09
     skipped
    -0.09
     شوند
    -0.08
    лоо
    -0.08
     hendes
    -0.08
     форум
    -0.08
     skip
    -0.08
    POSITIVE LOGITS
     method
    0.09
     meat
    0.07
    方法
    0.07
    Triple
    0.07
     argument
    0.07
     Ud
    0.07
     方法
    0.07
     subjects
    0.07
     reform
    0.07
    (subject
    0.07
    Activations Density 0.014%

    No Known Activations