© 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. 19-RESID-POST-AA
    11. 103172
    Prev
    Next
    INDEX
    Explanations

    arbitrary precision integers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HVAC
    -0.11
     sexist
    -0.08
     dryers
    -0.08
     FIFA
    -0.08
     minority
    -0.08
     CCTV
    -0.08
    /weather
    -0.08
     offenses
    -0.08
    :UITable
    -0.08
     televisión
    -0.08
    POSITIVE LOGITS
     arbitrary
    0.19
     bigint
    0.18
     Arbitr
    0.17
     GMP
    0.16
     Big
    0.15
     unlimited
    0.15
     mp
    0.15
     big
    0.15
    .Big
    0.15
    <Big
    0.14
    Activations Density 0.006%

    No Known Activations