© 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. 24560
    Prev
    Next
    INDEX
    Explanations

    color codes

    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
    태
    -0.08
     analyst
    -0.08
     dogging
    -0.08
    work
    -0.08
     সরকারি
    -0.07
     Pric
    -0.07
    fees
    -0.07
     forex
    -0.07
     fiscal
    -0.07
     Fiscal
    -0.07
    POSITIVE LOGITS
    Latency
    0.08
     oren
    0.08
     तेज
    0.08
     அக
    0.08
     hered
    0.08
     reproduc
    0.08
    碰
    0.08
    注意
    0.07
    检测
    0.07
    的方法
    0.07
    Activations Density 0.004%

    No Known Activations