© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 21914
    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
    Not in Any Lists

    No Comments

    Negative Logits
     inmigr
    -0.07
     Pollution
    -0.07
     താമ
    -0.07
     Refuge
    -0.07
    .repaint
    -0.07
    (mapping
    -0.07
    виж
    -0.07
    .uniform
    -0.07
    (convert
    -0.07
    czy
    -0.07
    POSITIVE LOGITS
     halves
    0.25
     split
    0.21
     halve
    0.20
     openen
    0.20
     geopend
    0.20
     splitting
    0.20
     geöffnet
    0.19
    split
    0.19
     opened
    0.19
    _split
    0.19
    Activations Density 0.015%

    No Known Activations