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. 15-RESID-POST-AA
    6. 19170
    Prev
    Next
    INDEX
    Explanations

    "

    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
     pilers
    -0.09
    .'));↵
    -0.09
    ?’↵↵
    -0.08
     akorn
    -0.08
    arnissaat
    -0.08
    .’↵↵
    -0.08
    ijent
    -0.08
     sulia
    -0.08
    qarnera
    -0.08
     პრო
    -0.08
    POSITIVE LOGITS
     "
    0.11
     
    0.10
     **
    0.09
       
    0.09
    "
    0.09
    這
    0.09
    �
    0.08
     #
    0.08
      
    0.08
     Invalid
    0.08
    Activations Density 0.038%

    No Known Activations