© 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. 11-RESID-POST-AA
    11. 26298
    Prev
    Next
    INDEX
    Explanations

    databases and cloud computing

    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
     Male
    -0.09
     Men's
    -0.09
    iritual
    -0.08
    Male
    -0.08
    男
    -0.08
    男子
    -0.08
    男性
    -0.08
     男
    -0.08
     vyb
    -0.08
     WPA
    -0.08
    POSITIVE LOGITS
     customers
    0.12
    业务
    0.12
     ग्राहक
    0.12
    Customers
    0.11
     customer
    0.11
     고객
    0.11
     Customers
    0.11
     ecommerce
    0.11
    客户
    0.11
     Customer
    0.11
    Activations Density 0.042%

    No Known Activations