Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 44273
    Prev
    Next
    INDEX
    Explanations

    powerful

    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
     fashions
    -0.08
    手续
    -0.08
     pauc
    -0.07
    /y
    -0.07
     asiat
    -0.07
    情况
    -0.07
    Attempt
    -0.07
    舍
    -0.07
    .Dep
    -0.07
    pañ
    -0.07
    POSITIVE LOGITS
     poderosa
    0.18
     powerful
    0.16
     puissant
    0.15
     Powerful
    0.15
     poderoso
    0.14
     krachtige
    0.14
     potente
    0.13
     puiss
    0.13
    力量
    0.13
     शक्त
    0.12
    Activations Density 0.068%

    No Known Activations