© 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. 99888
    Prev
    Next
    INDEX
    Explanations

    chemical reactions

    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
     vó
    -0.09
     ზოგ
    -0.09
     obligaciones
    -0.09
    ψεις
    -0.09
     тое
    -0.08
    翔
    -0.08
     отношения
    -0.08
     гады
    -0.08
    ებაში
    -0.08
    ffiti
    -0.08
    POSITIVE LOGITS
     catalysts
    0.17
     catalyst
    0.17
     catal
    0.15
     catalytic
    0.13
    催
    0.12
     Catal
    0.12
    -mediated
    0.11
     katal
    0.11
    Catal
    0.10
     Catalyst
    0.10
    Activations Density 0.008%

    No Known Activations