© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 109837
    Prev
    Next
    INDEX
    Explanations

    green

    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
    Negative Logits
     accommodations
    -0.09
     elektronische
    -0.08
     redux
    -0.08
     electronically
    -0.08
     accommodation
    -0.08
     izvr
    -0.07
     synthes
    -0.07
    	async
    -0.07
     formulas
    -0.07
     mindful
    -0.07
    POSITIVE LOGITS
    0.09
    obby
    0.08
    runde
    0.08
    -city
    0.07
    ayer
    0.07
    viz
    0.07
    Apartment
    0.07
    об
    0.07
    allen
    0.07
    Barcelona
    0.07
    Activations Density 2.069%
    No Known Activations