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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 60695
    Prev
    Next
    INDEX
    Explanations

    ar

    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
    �
    -0.07
    クト
    -0.07
    збекистон
    -0.07
    悲
    -0.07
    隆
    -0.07
    igenous
    -0.07
     teg
    -0.07
    -made
    -0.07
    ;↵↵
    -0.07
     toga
    -0.07
    POSITIVE LOGITS
     הנ
    0.08
     nuis
    0.08
    ?,
    0.07
     défin
    0.07
     વૈ
    0.07
     opcion
    0.07
     impat
    0.07
     nás
    0.07
     вим
    0.07
     және
    0.07
    Activations Density 0.007%

    No Known Activations