© 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. 45648
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     mott
    -0.09
    <Props
    -0.08
     inflam
    -0.08
    tick
    -0.08
    growth
    -0.07
     долго
    -0.07
    .eks
    -0.07
    openssl
    -0.07
    nutrition
    -0.07
    display
    -0.07
    POSITIVE LOGITS
     Contribution
    0.11
    Contribution
    0.10
     contribution
    0.10
     counted
    0.09
     subtraction
    0.09
     contributions
    0.09
     योगदान
    0.09
     Contributions
    0.09
     Beiträge
    0.09
     Count
    0.09
    Activations Density 0.031%

    No Known Activations