© 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. 108578
    Prev
    Next
    INDEX
    Explanations

    Information cutoff dates

    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
     Nä
    -0.08
     atuação
    -0.08
     ნ
    -0.08
    enburg
    -0.08
     nagbibigay
    -0.08
     מ
    -0.08
     uncomfortable
    -0.07
     preferência
    -0.07
     linkage
    -0.07
    යක්
    -0.07
    POSITIVE LOGITS
     latest
    0.09
     fictional
    0.08
     fixtures
    0.08
     Fixtures
    0.08
     forecast
    0.08
     заверш
    0.08
     sive
    0.08
     Patterns
    0.08
    Latest
    0.08
     collider
    0.08
    Activations Density 0.026%

    No Known Activations