© 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. 54470
    Prev
    Next
    INDEX
    Explanations

    muscle

    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
     degree
    -0.08
     карточ
    -0.08
    ED
    -0.07
    azini
    -0.07
    程度
    -0.06
    ண
    -0.06
    ää
    -0.06
     promised
    -0.06
     árbit
    -0.06
     الزمن
    -0.06
    POSITIVE LOGITS
     winds
    0.09
    Graw
    0.09
     ura
    0.08
     Tup
    0.08
     miejsce
    0.08
     מן
    0.08
     surrounds
    0.08
     transverse
    0.08
     কেউ
    0.08
     MUL
    0.08
    Activations Density 0.005%

    No Known Activations