© 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. 11-RESID-POST-AA
    11. 31082
    Prev
    Next
    INDEX
    Explanations

    labor

    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
    掲
    -0.09
    _NET
    -0.09
     Spam
    -0.08
    973
    -0.08
    φυ
    -0.08
     Investment
    -0.08
     excelencia
    -0.08
     empresario
    -0.08
     Blueprint
    -0.08
    اسب
    -0.08
    POSITIVE LOGITS
     onset
    0.09
     ждать
    0.08
     hyst
    0.08
     gyn
    0.08
    -muted
    0.08
     urgency
    0.08
     hormon
    0.08
    umble
    0.07
     sedation
    0.07
     Harris
    0.07
    Activations Density 0.003%

    No Known Activations