© 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. 18098
    Prev
    Next
    INDEX
    Explanations

    persists

    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
     constructions
    -0.08
     необходим
    -0.08
     allocations
    -0.08
    EEDED
    -0.08
     valuation
    -0.08
     gerekti
    -0.08
     кирәк
    -0.08
     қажетті
    -0.08
     nrho
    -0.08
     tokony
    -0.08
    POSITIVE LOGITS
     persists
    0.18
     persisted
    0.15
     persist
    0.14
    persist
    0.14
    .persist
    0.14
     pers
    0.13
     improving
    0.13
     verbeteren
    0.13
     Persist
    0.13
     Persistence
    0.12
    Activations Density 0.007%

    No Known Activations