© 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. 29424
    Prev
    Next
    INDEX
    Explanations

    chatbot/internet conversations

    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
    ाची
    -0.08
    िंग
    -0.08
     sinner
    -0.08
    ं
    -0.08
    ाचे
    -0.08
    .Empty
    -0.08
    -empty
    -0.08
    тик
    -0.08
     cantor
    -0.07
     sinners
    -0.07
    POSITIVE LOGITS
    Tipos
    0.08
    EX
    0.08
     EX
    0.08
     могу
    0.07
     yeux
    0.07
     Mab
    0.07
     hangt
    0.07
    =headers
    0.07
     poden
    0.07
    okea
    0.07
    Activations Density 0.003%

    No Known Activations