© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 19-RESID-POST-AA
    11. 21166
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sciously
    -0.10
    Mensaje
    -0.08
     Betrag
    -0.08
     Messages
    -0.08
     neurons
    -0.08
     planets
    -0.08
    entuk
    -0.08
     presum
    -0.08
     energies
    -0.08
    .setup
    -0.08
    POSITIVE LOGITS
     данные
    0.16
     data
    0.15
    最新
    0.14
     trends
    0.14
     डेटा
    0.14
     البيانات
    0.13
    数据
    0.13
     بيانات
    0.13
     tendências
    0.13
     最新
    0.13
    Activations Density 0.030%

    No Known Activations