© 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. 3-RESID-POST-AA
    11. 13371
    Prev
    Next
    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     micron
    -0.08
     Markus
    -0.08
     obt
    -0.08
    alve
    -0.07
     allure
    -0.07
    ിച്ചത്
    -0.07
     jamb
    -0.07
     сти
    -0.07
    manship
    -0.07
     interviewer
    -0.07
    POSITIVE LOGITS
    ancestor
    0.08
     strangers
    0.08
    Elementary
    0.08
    enemy
    0.08
     찾아
    0.08
    보험
    0.07
     पाया
    0.07
     lur
    0.07
     finne
    0.07
     transplant
    0.07
    Activations Density 0.018%

    No Known Activations