© 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. 20956
    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
    angenheit
    -0.08
    esteld
    -0.08
     miscar
    -0.08
     separators
    -0.08
    .ful
    -0.07
     locaux
    -0.07
     fechamento
    -0.07
     жив
    -0.07
    াছ
    -0.07
     blanks
    -0.07
    POSITIVE LOGITS
     exponent
    0.11
    指数
    0.09
    (mysql
    0.09
    Exponent
    0.09
     ցուց
    0.08
    (Authentication
    0.08
    ficiency
    0.08
     Index
    0.08
    (integer
    0.08
     Applying
    0.08
    Activations Density 0.007%

    No Known Activations