© 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. 45697
    Prev
    Next
    INDEX
    Explanations

    smooth functioning

    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
     प्रसिद्ध
    -0.07
    markup
    -0.07
     �
    -0.07
     रु
    -0.07
     hierfür
    -0.07
     damages
    -0.06
    文学
    -0.06
     వద్ద
    -0.06
     Curse
    -0.06
     ಬಳಿ
    -0.06
    POSITIVE LOGITS
     funcionamento
    0.14
     సాగ
    0.13
     funcionamiento
    0.12
     soepel
    0.12
     функциони
    0.12
    正常
    0.11
     uninterrupted
    0.11
     functioning
    0.11
     fonctionnement
    0.11
     déroule
    0.11
    Activations Density 0.044%

    No Known Activations