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. 111709
    Prev
    Next
    INDEX
    Explanations

    concerns

    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
     అనే
    -0.08
    \Schema
    -0.08
     tamamen
    -0.08
     largely
    -0.07
     كبير
    -0.07
     �
    -0.07
     మండ
    -0.07
     बुल
    -0.07
     $↵↵
    -0.07
     ਮੁ
    -0.07
    POSITIVE LOGITS
     wisdom
    0.09
     textbooks
    0.09
     textbook
    0.09
     suspects
    0.09
    套路
    0.08
     understandable
    0.08
     convention
    0.08
    之一
    0.08
    -standard
    0.08
     idi
    0.08
    Activations Density 0.201%

    No Known Activations