© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 47594
    Prev
    Next
    INDEX
    Explanations

    exceptions and limitations

    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
    走势
    -0.10
    劲
    -0.08
    此次
    -0.08
     આનંદ
    -0.08
    Klik
    -0.08
    快
    -0.08
    VBox
    -0.08
    miz
    -0.08
    /output
    -0.08
    颜色
    -0.08
    POSITIVE LOGITS
     exemptions
    0.16
     exceptions
    0.13
     exemption
    0.12
     criteria
    0.12
     Exceptions
    0.12
    exceptions
    0.12
     allowances
    0.12
     exempt
    0.12
     critères
    0.11
     नियम
    0.11
    Activations Density 0.064%

    No Known Activations