© 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. 22075
    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
     Stitch
    -0.08
     quarant
    -0.08
     stap
    -0.08
     upholstery
    -0.08
     warmed
    -0.07
     safe
    -0.07
    ============
    -0.07
     cuar
    -0.07
     Datei
    -0.07
     обработ
    -0.07
    POSITIVE LOGITS
     magnitude
    0.17
    Magnitude
    0.15
    长度
    0.13
    agnitude
    0.13
     comprimento
    0.13
     дли
    0.13
     ||
    0.12
     Länge
    0.12
     lengths
    0.12
     length
    0.12
    Activations Density 0.014%

    No Known Activations