© 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. 47378
    Prev
    Next
    INDEX
    Explanations

    Chinese character counts

    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
     dep
    -0.08
     Genesis
    -0.08
    IGIN
    -0.08
     lesa
    -0.08
     NOAA
    -0.08
     Kens
    -0.07
     Donec
    -0.07
     posao
    -0.07
     Rien
    -0.07
     incum
    -0.07
    POSITIVE LOGITS
    と言
    0.08
    是多少
    0.08
     glorious
    0.08
     fysieke
    0.08
     refers
    0.07
     euros
    0.07
     pixels
    0.07
     restrictions
    0.07
     minutes
    0.07
     paragraph
    0.07
    Activations Density 0.017%

    No Known Activations