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. 120352
    Prev
    Next
    INDEX
    Explanations

    Code structure delimiters

    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
     aptitude
    -0.09
     enctype
    -0.09
     cognitive
    -0.08
     airtight
    -0.08
     deeb
    -0.08
     domicile
    -0.08
     sabor
    -0.08
    Clinical
    -0.08
     yub
    -0.08
     praz
    -0.08
    POSITIVE LOGITS
     vegetation
    0.12
     scenery
    0.12
    景
    0.11
     greenery
    0.11
     foliage
    0.10
    /icons
    0.09
     silhou
    0.09
    Backdrop
    0.09
    湖
    0.09
     backdrop
    0.09
    Activations Density 0.072%

    No Known Activations