© 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. 79409
    Prev
    Next
    INDEX
    Explanations

    the

    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
    比较
    -0.08
    /functions
    -0.08
     Vinyl
    -0.08
    ष्ट
    -0.08
     PVC
    -0.08
    ynchronous
    -0.08
    比較
    -0.08
    えて
    -0.08
    alar
    -0.07
     gouvernement
    -0.07
    POSITIVE LOGITS
     famously
    0.12
     iconic
    0.11
     prestigious
    0.11
     famous
    0.11
     pinnacle
    0.11
     famed
    0.10
     знаменит
    0.09
     famosa
    0.09
     annual
    0.09
     beroemde
    0.09
    Activations Density 0.017%

    No Known Activations