© 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. 19-RESID-POST-AA
    11. 17969
    Prev
    Next
    INDEX
    Explanations

    languages

    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
    Negative Logits
     evaluates
    -0.09
     crít
    -0.09
    �
    -0.09
    anship
    -0.09
    ğlu
    -0.08
     revis
    -0.08
    	ASSERT
    -0.08
    지털
    -0.08
    ushu
    -0.08
     ree
    -0.08
    POSITIVE LOGITS
     сложности
    0.09
     coordinator
    0.08
     learners
    0.08
    Begin
    0.08
     Classe
    0.08
     עם
    0.08
    listener
    0.08
     emitter
    0.08
    -learning
    0.08
     learner
    0.08
    Activations Density 0.003%

    No Known Activations