© 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. 65587
    Prev
    Next
    INDEX
    Explanations

    Oda Nobunaga, samurai

    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
     hypoc
    -0.08
    rospection
    -0.08
     linewidth
    -0.08
     прибор
    -0.08
    utin
    -0.08
     ageing
    -0.08
     municip
    -0.08
     разговор
    -0.08
     conform
    -0.08
     envel
    -0.07
    POSITIVE LOGITS
     camps
    0.08
     Queens
    0.08
     defeating
    0.08
    ケット
    0.08
     aggregate
    0.07
     Shri
    0.07
     castles
    0.07
    �
    0.07
     wrestler
    0.07
     memperoleh
    0.07
    Activations Density 0.003%

    No Known Activations