© 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. 94557
    Prev
    Next
    INDEX
    Explanations

    skepticism and disbelief

    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
     ship
    -0.09
     umo
    -0.08
     symbole
    -0.07
     noto
    -0.07
     incorrectly
    -0.07
     rake
    -0.07
     rollback
    -0.07
    冻结
    -0.07
     गल
    -0.07
    गल
    -0.07
    POSITIVE LOGITS
    可靠
    0.12
    可信
    0.12
     reliable
    0.12
     fiables
    0.12
     믿
    0.11
     trusting
    0.11
     fiable
    0.11
     betrouwbaar
    0.11
    可靠吗
    0.11
     trustworthy
    0.11
    Activations Density 0.035%

    No Known Activations