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

    Neuronpedia

    APICircuit 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. 88313
    Prev
    Next
    INDEX
    Explanations

    Conversational text

    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
     aé
    -0.08
     personajes
    -0.07
     vidas
    -0.07
     prioridades
    -0.07
     parece
    -0.07
     enemigos
    -0.07
     webpack
    -0.07
     salários
    -0.07
    _half
    -0.07
     методом
    -0.07
    POSITIVE LOGITS
     Disclaimer
    0.10
     강조
    0.10
     ressalt
    0.09
     disclaimer
    0.09
     подчерк
    0.09
     benadr
    0.09
     souligne
    0.09
     erklären
    0.08
     กล่าวว่า
    0.08
    atatables
    0.08
    Activations Density 0.076%

    No Known Activations