© 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. 1119
    Prev
    Next
    INDEX
    Explanations

    factual accuracy

    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
     wachsen
    -0.09
     igra
    -0.08
    怎么玩
    -0.08
    Converter
    -0.08
    -0.07
    (Motion
    -0.07
     यानी
    -0.07
     subito
    -0.07
    .sms
    -0.07
     continuación
    -0.07
    POSITIVE LOGITS
     misinformation
    0.17
     inaccuracies
    0.13
     inaccurate
    0.13
     factual
    0.12
     Incorrect
    0.11
     incorrect
    0.11
     trustworthy
    0.11
    accur
    0.11
     erroneous
    0.11
    准确
    0.11
    Activations Density 0.019%
    No Known Activations