© 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. 103194
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     öffentliche
    -0.08
     सार्वजनिक
    -0.07
     offent
    -0.07
     공개
    -0.07
     public
    -0.07
     dgv
    -0.07
     QFile
    -0.07
     ಸಾರ್ವಜನಿಕ
    -0.07
     city
    -0.07
    Zend
    -0.07
    POSITIVE LOGITS
    Now
    0.08
    וחד
    0.08
     cutest
    0.08
     placebo
    0.08
    okot
    0.08
     ahora
    0.08
    ()),
    0.08
    	now
    0.08
    )),↵
    0.08
    ithand
    0.08
    Activations Density 0.001%

    No Known Activations