© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30468
    Prev
    Next
    INDEX
    Explanations

    Flashcards and quizzes

    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
     controvers
    -0.09
    	strcat
    -0.09
    joining
    -0.08
    万人
    -0.08
     hieman
    -0.08
     strcat
    -0.08
     män
    -0.08
    哲
    -0.08
     handbook
    -0.08
     mennesker
    -0.08
    POSITIVE LOGITS
     जवाब
    0.09
     verbal
    0.08
     रोल
    0.08
     solicit
    0.08
     quizzes
    0.08
     idé
    0.08
     reverse
    0.07
    .flip
    0.07
     modalities
    0.07
     flip
    0.07
    Activations Density 0.012%

    No Known Activations