© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 95530
    Prev
    Next
    INDEX
    Explanations

    Two

    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
    Outlet
    -0.08
     Neust
    -0.08
    패
    -0.07
    ouille
    -0.07
     crois
    -0.07
     STE
    -0.07
     właśnie
    -0.07
     Jem
    -0.07
     him
    -0.07
    Pisc
    -0.07
    POSITIVE LOGITS
     secondly
    0.08
    	resolve
    0.08
     Subsequently
    0.08
     Cycl
    0.08
     consiste
    0.07
     всю
    0.07
    	input
    0.07
     Hale
    0.07
     chemicals
    0.07
    易
    0.07
    Activations Density 0.079%

    No Known Activations