© 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. 23117
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     different
    -0.13
     nuovo
    -0.11
     nuevo
    -0.11
     nueva
    -0.10
     νέο
    -0.10
     కొత్త
    -0.10
     changing
    -0.10
     nuevas
    -0.10
     nieuwe
    -0.10
     diferentes
    -0.10
    POSITIVE LOGITS
    ≤
    0.13
     ≤
    0.12
    ]<=
    0.12
     maksimal
    0.11
     <=
    0.11
    <=
    0.10
     максимально
    0.10
    )<=
    0.09
     이하
    0.09
    manageable
    0.09
    Activations Density 0.063%

    No Known Activations