© 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. 99637
    Prev
    Next
    INDEX
    Explanations

    Write in Russian

    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
    astern
    -0.08
    ouple
    -0.08
    었던
    -0.07
     vorz
    -0.07
     simplic
    -0.07
     recherchez
    -0.07
     saine
    -0.07
     Angehör
    -0.07
    اران
    -0.07
    <?,
    -0.07
    POSITIVE LOGITS
     Nud
    0.07
    ચાલ
    0.07
    :void
    0.07
     kj
    0.07
    0.07
    kj
    0.07
    不停
    0.07
     Lov
    0.07
     kw
    0.07
    Proc
    0.07
    Activations Density 0.009%
    No Known Activations