© 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. 108423
    Prev
    Next
    INDEX
    Explanations

    это

    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
     уда
    -0.09
    oyi
    -0.07
     ])↵↵
    -0.07
    fan
    -0.07
     ayy
    -0.07
     firewall
    -0.07
     arbeitet
    -0.07
    iliy
    -0.07
     struck
    -0.07
     todėl
    -0.07
    POSITIVE LOGITS
    分别
    0.09
    剩
    0.08
     Calle
    0.08
    CPA
    0.08
     deodor
    0.08
     美
    0.08
    _impl
    0.08
    女性
    0.08
     beaut
    0.08
    貌
    0.08
    Activations Density 0.000%

    No Known Activations