© 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. 29082
    Prev
    Next
    INDEX
    Explanations

    handy

    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
     Plateau
    -0.08
    大陆
    -0.07
     Ende
    -0.07
    uros
    -0.07
     aanb
    -0.07
    年以上
    -0.07
     Dentistry
    -0.07
    त्र
    -0.07
     gon
    -0.07
     Shaw
    -0.07
    POSITIVE LOGITS
     handy
    0.09
     helpful
    0.09
     útiles
    0.08
     совет
    0.08
     handig
    0.08
    ಳಿತ
    0.08
    Helpful
    0.08
    妙
    0.08
     plasm
    0.08
    ंका
    0.08
    Activations Density 0.007%

    No Known Activations