© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 69777
    Prev
    Next
    INDEX
    Explanations

    Selector

    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
     honorable
    -0.09
     honoring
    -0.09
    _initialize
    -0.08
     companions
    -0.08
     Opt
    -0.08
    oplevel
    -0.08
    -0.08
     sealed
    -0.08
     комплек
    -0.08
     لإن
    -0.08
    POSITIVE LOGITS
     redux
    0.10
    _SELECTOR
    0.09
     accessing
    0.09
    总书记
    0.09
     extractor
    0.08
     subscribed
    0.08
    (select
    0.08
     retrieves
    0.08
    /select
    0.08
    Redux
    0.08
    Activations Density 0.002%
    No Known Activations