© 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. 95705
    Prev
    Next
    INDEX
    Explanations

    news events

    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
    иба
    -0.08
    оян
    -0.08
    íveis
    -0.07
     claros
    -0.07
    。そして
    -0.07
     کبھی
    -0.07
     likewise
    -0.07
    //↵//
    -0.07
    های
    -0.07
     guessing
    -0.07
    POSITIVE LOGITS
    旨
    0.09
     originated
    0.09
     bedoeld
    0.09
     belonged
    0.08
     berasal
    0.08
     originate
    0.08
     Revel
    0.08
     antih
    0.07
     befindet
    0.07
    eyd
    0.07
    Activations Density 0.310%

    No Known Activations