© 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. 23-RESID-POST-AA
    11. 49475
    Prev
    Next
    INDEX
    Explanations

    Food ingredients

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     benchmarking
    -0.08
     User
    -0.08
     Respond
    -0.08
     IDisposable
    -0.08
     capabilities
    -0.08
    平台官网
    -0.08
     пандем
    -0.08
    Capabilities
    -0.08
    道路
    -0.08
     সাক্ষ
    -0.08
    POSITIVE LOGITS
     puree
    0.21
     mozzarella
    0.21
     yogurt
    0.20
     sauce
    0.19
     vegetables
    0.19
     roasted
    0.19
     veggies
    0.19
     toasted
    0.19
     овощ
    0.19
     salad
    0.19
    Activations Density 0.373%

    No Known Activations