© 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. 3-RESID-POST-AA
    11. 3029
    Prev
    Next
    INDEX
    Explanations

    comment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     conta
    -0.08
    ello
    -0.08
     wrinkles
    -0.08
    -0.07
     Kale
    -0.07
    כל
    -0.07
     kale
    -0.07
     bread
    -0.07
     counter
    -0.07
     Adrian
    -0.06
    POSITIVE LOGITS
     अधिकारी
    0.08
     gesch
    0.08
    orse
    0.07
    -operated
    0.07
     pleas
    0.07
     tant
    0.07
     songwriting
    0.07
    िइ
    0.07
     ""
↵
    0.07
    road
    0.07
    Activations Density 0.082%
    No Known Activations