© 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. 16609
    Prev
    Next
    INDEX
    Explanations

    geometry problems

    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
     Ros
    -0.08
     shampoo
    -0.07
     szer
    -0.07
    -0.07
    po
    -0.07
     speak
    -0.07
     Channels
    -0.07
     sonar
    -0.07
    -0.06
     felis
    -0.06
    POSITIVE LOGITS
    есе
    0.09
    -ан
    0.09
     अलग
    0.09
    -व
    0.09
    최근
    0.09
    ajad
    0.09
    Trong
    0.09
     встр
    0.08
     көрс
    0.08
     entsprechend
    0.08
    Activations Density 0.006%
    No Known Activations