© 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. 94616
    Prev
    Next
    INDEX
    Explanations

    prime numbers

    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
    'amb
    -0.08
     presencial
    -0.08
    'm
    -0.08
     perju
    -0.08
     three
    -0.08
     Persons
    -0.08
    ণ্ট
    -0.08
    溪
    -0.07
    ございました
    -0.07
     chí
    -0.07
    POSITIVE LOGITS
    _except
    0.08
     лік
    0.08
    -backed
    0.08
     भग
    0.08
     domination
    0.08
     satur
    0.07
     impregn
    0.07
     sieve
    0.07
     rook
    0.07
     Honey
    0.07
    Activations Density 0.012%

    No Known Activations