© 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. 18153
    Prev
    Next
    INDEX
    Explanations

    balance

    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
     comprehension
    -0.07
     arv
    -0.07
    юч
    -0.07
     qiym
    -0.07
     üç
    -0.07
     velocidade
    -0.07
     viviendas
    -0.07
    fim
    -0.07
    family
    -0.07
    _MULTI
    -0.07
    POSITIVE LOGITS
     imbalance
    0.24
     balanced
    0.21
     balances
    0.21
     Balanced
    0.20
    balanced
    0.20
    Balance
    0.20
    balance
    0.20
    _balance
    0.20
    Balanced
    0.20
     Balance
    0.20
    Activations Density 0.055%

    No Known Activations