© 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. 108115
    Prev
    Next
    INDEX
    Explanations

    Equations/mathematical logic

    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
    sz
    -0.08
     krijg
    -0.08
     nadr
    -0.08
    fos
    -0.08
    免費
    -0.07
     avo
    -0.07
    753
    -0.07
    这么
    -0.07
    GT
    -0.07
    ，而且
    -0.07
    POSITIVE LOGITS
     hingegen
    0.15
    則
    0.13
    则
    0.13
     invece
    0.10
     మాత్రం
    0.10
     isə
    0.10
     likewise
    0.09
     schließlich
    0.09
     naman
    0.09
     dagegen
    0.09
    Activations Density 0.150%

    No Known Activations