© 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. 23-RESID-POST-AA
    11. 48875
    Prev
    Next
    INDEX
    Explanations

    Business, money, or economics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ég
    -0.09
     الجمع
    -0.08
     gabe
    -0.08
    ਆ
    -0.08
     pretending
    -0.08
    ETYPE
    -0.08
    ય
    -0.08
     abolished
    -0.08
     permettent
    -0.08
     عبد
    -0.08
    POSITIVE LOGITS
    tract
    0.12
    tracted
    0.11
    tractor
    0.10
    roads
    0.09
    odes
    0.08
    traction
    0.08
    ks
    0.08
    ollars
    0.08
     boosting
    0.08
     homework
    0.07
    Activations Density 0.000%

    No Known Activations