© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 129266
    Prev
    Next
    INDEX
    Explanations

    crimination

    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
    .collection
    -0.08
    .collections
    -0.08
    collections
    -0.07
     magnetic
    -0.07
    HL
    -0.07
    ocoder
    -0.07
    .conv
    -0.07
    #↵
    -0.07
    给予
    -0.07
     Vict
    -0.07
    POSITIVE LOGITS
     넣
    0.08
     Ό
    0.07
     ό
    0.07
     Weapons
    0.07
     ग
    0.07
     руки
    0.07
     Holy
    0.07
     президента
    0.07
    -gh
    0.07
     harm
    0.07
    Activations Density 0.000%

    No Known Activations