© 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. 44630
    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
    炼
    -0.08
    学习
    -0.08
    ificacion
    -0.08
     landmark
    -0.08
    春节
    -0.08
    执
    -0.08
    功能
    -0.08
    奋
    -0.07
    来
    -0.07
    关键
    -0.07
    POSITIVE LOGITS
    Magazine
    0.09
     magazines
    0.08
    Convertible
    0.08
    otic
    0.08
    ........................
    0.08
    .slider
    0.08
    Converters
    0.07
    BOR
    0.07
    ته
    0.07
    Digit
    0.07
    Activations Density 0.002%

    No Known Activations