© 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. 23-RESID-POST-AA
    11. 5601
    Prev
    Next
    INDEX
    Explanations

    orit

    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
    Monthly
    -0.08
     Monthly
    -0.08
     monthly
    -0.08
    icie
    -0.08
    yele
    -0.08
    aya
    -0.08
     anual
    -0.07
     yearly
    -0.07
    ye
    -0.07
     integer
    -0.07
    POSITIVE LOGITS
    mo
    0.12
    orit
    0.09
    ുന്നതിന
    0.09
    ması
    0.08
    ativamente
    0.08
    arsuaq
    0.08
     mo
    0.08
    μο
    0.08
     algoritmo
    0.07
    .transform
    0.07
    Activations Density 0.000%

    No Known Activations