© 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. 15-RESID-POST-AA
    11. 16710
    Prev
    Next
    INDEX
    Explanations

    Brackets/parentheses/symbols

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intricate
    -0.07
    却
    -0.07
     seekers
    -0.07
    /(
    -0.07
     letzt
    -0.07
    ింది
    -0.07
     seeking
    -0.07
    最终
    -0.07
     Durham
    -0.07
     обе
    -0.07
    POSITIVE LOGITS
     deuxième
    0.10
     arall
    0.09
     drugo
    0.09
     toinen
    0.09
     δεύτε
    0.09
     번째
    0.08
    Another
    0.08
     अर्को
    0.08
     tjetër
    0.08
     दूसरा
    0.08
    Activations Density 0.024%

    No Known Activations