© 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. 63956
    Prev
    Next
    INDEX
    Explanations

    alternative possibilities

    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
    apas
    -0.08
    maximize
    -0.08
    provided
    -0.08
     vlo
    -0.08
    desired
    -0.08
     PROVIDED
    -0.08
    Diagonal
    -0.08
    -approved
    -0.08
    experiment
    -0.08
    aup
    -0.08
    POSITIVE LOGITS
     referring
    0.10
     refiere
    0.10
     unfamiliar
    0.09
     interpreting
    0.09
     ниш
    0.09
     beziehen
    0.08
     rifer
    0.08
     unemployment
    0.08
    猜
    0.08
     קשר
    0.08
    Activations Density 0.065%

    No Known Activations