© 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. 68756
    Prev
    Next
    INDEX
    Explanations

    Building stories

    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
     päivän
    -0.09
    했던
    -0.09
    骗子
    -0.08
     لبعض
    -0.08
     einiger
    -0.08
     κατάσταση
    -0.08
    Builtin
    -0.08
     kubona
    -0.08
     sytu
    -0.08
     junit
    -0.08
    POSITIVE LOGITS
     skeleton
    0.09
     stacked
    0.09
    施工
    0.09
     stagger
    0.09
     massive
    0.08
     scaffold
    0.08
     blueprint
    0.08
     planned
    0.08
     Staffing
    0.08
    建设
    0.08
    Activations Density 0.038%

    No Known Activations