© 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. 94640
    Prev
    Next
    INDEX
    Explanations

    at-will employment

    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
     quilt
    -0.08
    ارش
    -0.08
     queued
    -0.08
    秦
    -0.08
     ANSI
    -0.07
     quotas
    -0.07
    いっぱい
    -0.07
    Quota
    -0.07
    emen
    -0.07
    意见
    -0.07
    POSITIVE LOGITS
     terap
    0.08
    מר
    0.08
     transferring
    0.08
    ్యంలో
    0.07
     relocating
    0.07
    தில்
    0.07
     тұ
    0.07
     động
    0.07
    âm
    0.07
     대부분
    0.07
    Activations Density 0.001%

    No Known Activations