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. 53784
    Prev
    Next
    INDEX
    Explanations

    software 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
    ╗
    -0.10
    แก่
    -0.10
     testimonial
    -0.09
     winger
    -0.09
     workmanship
    -0.09
     वालों
    -0.09
     wearer
    -0.08
    满
    -0.08
    -half
    -0.08
     Constitution
    -0.08
    POSITIVE LOGITS
    Multi
    0.09
     Multi
    0.09
    GN
    0.08
     APIs
    0.08
    G
    0.08
     Linux
    0.08
    API
    0.08
    Bee
    0.08
     API
    0.08
    SQL
    0.08
    Activations Density 0.061%

    No Known Activations