Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 15-RESID-POST-AA
    6. 106
    Prev
    Next
    INDEX
    Explanations

    dialog scenes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Baccarat
    -0.10
     王者
    -0.10
     Влад
    -0.09
     baccarat
    -0.09
     Lietuvos
    -0.09
     Atendimento
    -0.09
     Bunifu
    -0.09
     inimene
    -0.09
     Văn
    -0.09
     Сондықтан
    -0.09
    POSITIVE LOGITS
     skeptical
    0.10
       
    0.08
     wary
    0.08
      
    0.08
        
    0.08
    (
    0.08
     is
    0.08
     worried
    0.08
    /
    0.08
     skepticism
    0.07
    Activations Density 0.014%

    No Known Activations