© 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. 19-RESID-POST-AA
    11. 102606
    Prev
    Next
    INDEX
    Explanations

    remaining

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     шарт
    -0.08
     כיצד
    -0.08
     কী
    -0.08
     bagaimana
    -0.07
     процес
    -0.07
    -0.07
    laştır
    -0.07
     如何
    -0.07
     qanday
    -0.07
     hvernig
    -0.07
    POSITIVE LOGITS
    剩
    0.21
     restantes
    0.19
     remaining
    0.19
     остальные
    0.18
    remaining
    0.18
     बाकी
    0.17
     остав
    0.17
     Remaining
    0.17
     leaving
    0.17
    Remaining
    0.17
    Activations Density 0.046%
    No Known Activations