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. 76413
    Prev
    Next
    INDEX
    Explanations

    mathematical word problems

    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
    ulence
    -0.09
    arus
    -0.08
     memper
    -0.08
     ಬೇ
    -0.07
     Heidi
    -0.07
    memcmp
    -0.07
     Зам
    -0.07
    	  
    -0.07
     aside
    -0.07
     થોડ
    -0.07
    POSITIVE LOGITS
    /how
    0.09
    씩
    0.08
    是多少
    0.08
     именно
    0.08
     soll
    0.08
     razy
    0.08
    ုံး
    0.08
    ever
    0.08
     pedestal
    0.07
     Hunting
    0.07
    Activations Density 0.025%

    No Known Activations