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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 102691
    Prev
    Next
    INDEX
    Explanations

    Brain anatomy

    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
    -used
    -0.09
     Gover
    -0.08
     مربوط
    -0.08
     பயன்படுத்த
    -0.08
     arụ
    -0.08
     governs
    -0.08
    kwọ
    -0.08
     Eats
    -0.08
    _used
    -0.08
     Bikes
    -0.08
    POSITIVE LOGITS
     pulv
    0.12
     haben
    0.12
     reuni
    0.11
     nucleus
    0.11
     th
    0.11
     medial
    0.10
     anterior
    0.09
     posterior
    0.09
     hebben
    0.09
     thym
    0.09
    Activations Density 0.006%

    No Known Activations