© 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. 23-RESID-POST-AA
    11. 49567
    Prev
    Next
    INDEX
    Explanations

    maximum

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Costs
    -0.09
    ့်
    -0.08
     Those
    -0.08
     بعضها
    -0.08
     Smy
    -0.08
     Prices
    -0.08
     volt
    -0.08
     hər
    -0.08
     မှ
    -0.08
    /she
    -0.08
    POSITIVE LOGITS
     number
    0.13
     #
    0.12
     distinct
    0.11
     possible
    0.10
     we
    0.10
     you
    0.10
     guarantee
    0.10
     unique
    0.10
    Distinct
    0.10
    _is
    0.10
    Activations Density 0.041%

    No Known Activations