© 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 EvalsExportsAPI 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. 20406
    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
     gyms
    -0.10
     Elev
    -0.09
     elders
    -0.09
     elevate
    -0.09
     Elevated
    -0.09
     weddings
    -0.09
    ivir
    -0.09
    Elevation
    -0.09
     sneakers
    -0.09
     elder
    -0.09
    POSITIVE LOGITS
     digits
    0.18
    _digits
    0.15
    Digits
    0.15
    digits
    0.15
     digit
    0.13
     infinitely
    0.12
     decimals
    0.12
     infinite
    0.12
     циф
    0.12
     decimal
    0.12
    Activations Density 0.022%

    No Known Activations