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. 30698
    Prev
    Next
    INDEX
    Explanations

    {

    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
     gout
    -0.08
     intangible
    -0.08
     منف
    -0.07
    চিত
    -0.07
    .githubusercontent
    -0.07
    /or
    -0.07
     berichtet
    -0.07
     سما
    -0.07
     의해
    -0.07
     disg
    -0.07
    POSITIVE LOGITS
    
    ↵
    
    ↵
    0.08
     amb
    0.08
    basename
    0.08
       ↵
    0.08
    

    0.08
     essentials
    0.08
     esempio
    0.07
     KW
    0.07
     Amb
    0.07
    draft
    0.07
    Activations Density 0.013%

    No Known Activations