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. 112874
    Prev
    Next
    INDEX
    Explanations

    mathematical domain

    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
     Constitucional
    -0.08
    概要
    -0.08
    जब
    -0.07
     ochtend
    -0.07
     maintien
    -0.07
    асс
    -0.07
    erring
    -0.07
     जब
    -0.07
    bug
    -0.07
     tó
    -0.07
    POSITIVE LOGITS
     easily
    0.08
     sobra
    0.08
     pū
    0.07
     Easily
    0.07
     enkelt
    0.07
    oci
    0.07
     Division
    0.07
     división
    0.07
     nothing
    0.07
     straightforward
    0.07
    Activations Density 0.052%

    No Known Activations