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. 76030
    Prev
    Next
    INDEX
    Explanations

    )

    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
    forth
    -0.08
    melon
    -0.08
    তম
    -0.07
    .Date
    -0.07
    287
    -0.07
    ి
    -0.07
     preju
    -0.07
     procès
    -0.07
     Назар
    -0.07
    ifiable
    -0.07
    POSITIVE LOGITS
    щу
    0.08
    .wikipedia
    0.08
    рок
    0.08
    иров
    0.07
    نية
    0.07
     histó
    0.07
    uedes
    0.07
     mann
    0.07
     spør
    0.07
    tersom
    0.07
    Activations Density 0.029%

    No Known Activations