© 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. 45783
    Prev
    Next
    INDEX
    Explanations

    ibraries

    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
    	st
    -0.08
    ്റ്റ
    -0.07
    ിട്ട്
    -0.07
    ിരുന്ന
    -0.07
     Jésus
    -0.07
    ീഷ
    -0.07
     asym
    -0.07
     --↵
    -0.07
    ാങ
    -0.07
    Hi
    -0.07
    POSITIVE LOGITS
     Annot
    0.08
     Innenstadt
    0.08
     generado
    0.07
     docket
    0.07
     splet
    0.07
     Architects
    0.07
     legalized
    0.07
    енью
    0.07
     reflect
    0.07
    ientemente
    0.07
    Activations Density 0.000%

    No Known Activations