© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 113599
    Prev
    Next
    INDEX
    Explanations

    Nuclear energy

    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
     (__
    -0.09
     bantu
    -0.09
     repell
    -0.08
    Photography
    -0.08
     UICollection
    -0.08
    .squeeze
    -0.08
     Instagram
    -0.08
     admirer
    -0.08
     ઘરે
    -0.08
     songwriter
    -0.08
    POSITIVE LOGITS
     safety
    0.10
     Safety
    0.10
     안전
    0.10
     सुरक्षा
    0.10
    Safety
    0.10
     veiligheids
    0.10
     upgrades
    0.10
    _shutdown
    0.09
    、安全
    0.09
    安全
    0.09
    Activations Density 0.016%

    No Known Activations