© 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. 23-RESID-POST-AA
    11. 97629
    Prev
    Next
    INDEX
    Explanations

    file paths and code

    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
    ediation
    -0.09
     opbreng
    -0.09
     outfits
    -0.08
     accommodatie
    -0.08
     vacation
    -0.08
    édit
    -0.08
     outfit
    -0.08
    eien
    -0.08
     vent
    -0.08
     mídia
    -0.08
    POSITIVE LOGITS
     Hard
    0.08
     Lisp
    0.08
     языка
    0.07
     సర
    0.07
     önem
    0.07
     ಬು
    0.07
     Bank
    0.07
     连
    0.07
    عدة
    0.07
    Hard
    0.07
    Activations Density 0.001%

    No Known Activations