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. 51
    Prev
    Next
    INDEX
    Explanations

    order

    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
     genoemde
    -0.08
     Hug
    -0.08
     Bruins
    -0.08
     Lub
    -0.08
    унок
    -0.07
     ponud
    -0.07
    među
    -0.07
     біблі
    -0.07
     Meets
    -0.07
     oğ
    -0.07
    POSITIVE LOGITS
         ↵↵
    0.10
       ↵↵
    0.09
          ↵↵
    0.09
      ↵    ↵
    0.09
       ↵    ↵
    0.09
      ↵↵↵
    0.08
        ↵↵
    0.08
           ↵
    0.08
      ↵↵
    0.08
     (
    0.08
    Activations Density 0.490%

    No Known Activations