© 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. 91579
    Prev
    Next
    INDEX
    Explanations

    book

    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
     iconic
    -0.08
    achos
    -0.08
     notorious
    -0.08
     configure
    -0.08
     claimant
    -0.08
    ach
    -0.08
     configured
    -0.08
     infamous
    -0.07
    sqrt
    -0.07
    configure
    -0.07
    POSITIVE LOGITS
     veröff
    0.11
    を書く
    0.10
     publié
    0.10
     veröffentlicht
    0.10
     publicada
    0.09
     schrijven
    0.09
    出版
    0.09
     প্রকাশ
    0.09
     publicado
    0.09
     Poems
    0.09
    Activations Density 0.117%

    No Known Activations