© 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. 30274
    Prev
    Next
    INDEX
    Explanations

    Story excerpts

    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
    imum
    -0.08
     globalization
    -0.07
    Arab
    -0.07
    شطة
    -0.07
     intenso
    -0.07
     promote
    -0.07
     упражнения
    -0.07
     anabolic
    -0.07
    outin
    -0.07
    .prom
    -0.07
    POSITIVE LOGITS
     revelation
    0.14
     revelations
    0.13
    了解到
    0.13
    揭秘
    0.13
    揭
    0.11
     revealed
    0.11
     Revelation
    0.11
     erzählt
    0.11
    透露
    0.11
     выяс
    0.10
    Activations Density 0.125%

    No Known Activations