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. 43862
    Prev
    Next
    INDEX
    Explanations

    tools

    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
     chemically
    -0.08
    ämä
    -0.08
    Occurs
    -0.08
    lə
    -0.08
     दश
    -0.08
     विदेशी
    -0.08
    -0.07
    樣
    -0.07
     xảy
    -0.07
     divisible
    -0.07
    POSITIVE LOGITS
     tools
    0.15
    工具
    0.15
     herramientas
    0.14
     ferramentas
    0.14
     Tools
    0.13
     ابزار
    0.13
    tools
    0.13
     strumenti
    0.13
    _tools
    0.12
     outils
    0.12
    Activations Density 0.066%

    No Known Activations