© 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. 78008
    Prev
    Next
    INDEX
    Explanations

    linguistics

    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
     severely
    -0.08
    .nt
    -0.08
    Export
    -0.08
     negatively
    -0.08
    -0.08
     vasta
    -0.08
     largely
    -0.08
     drastically
    -0.08
     er
    -0.08
    .Export
    -0.08
    POSITIVE LOGITS
    表示
    0.10
     verbs
    0.09
    詞
    0.09
     표시
    0.09
    词
    0.09
    -cap
    0.09
     nouns
    0.09
     Wörter
    0.08
     pouch
    0.08
     lautet
    0.08
    Activations Density 0.008%
    No Known Activations