© 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. 47415
    Prev
    Next
    INDEX
    Explanations

    comfort

    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
     conhecimento
    -0.09
    Helping
    -0.09
    луж
    -0.08
     conhece
    -0.08
     actes
    -0.08
     Organized
    -0.08
     úteis
    -0.08
     संस्क
    -0.08
     conoscere
    -0.08
    .cor
    -0.08
    POSITIVE LOGITS
     straps
    0.10
     strap
    0.09
     wear
    0.09
    komfort
    0.09
     endurance
    0.09
     chew
    0.08
    -through
    0.08
    佩
    0.08
     الدرا
    0.08
     पहन
    0.08
    Activations Density 0.013%

    No Known Activations