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. 117377
    Prev
    Next
    INDEX
    Explanations

    falls

    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
     chang
    -0.08
     thy
    -0.08
     PMS
    -0.08
     Nicolas
    -0.08
     nearing
    -0.07
     Niem
    -0.07
    edf
    -0.07
     derives
    -0.07
    765
    -0.07
    inish
    -0.07
    POSITIVE LOGITS
     categoria
    0.10
     catégorie
    0.09
    カテゴリー
    0.09
    属于
    0.09
     categoría
    0.09
     category
    0.08
     Category
    0.08
     categorías
    0.08
     destacar
    0.08
     Kategorie
    0.08
    Activations Density 0.019%

    No Known Activations