© 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. 19437
    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
     vicinity
    -0.08
    traction
    -0.08
    supports
    -0.08
    industrie
    -0.08
    kua
    -0.08
     недвижимости
    -0.08
    ريس
    -0.07
     покупке
    -0.07
     kies
    -0.07
    omento
    -0.07
    POSITIVE LOGITS
     letters
    0.19
    _letters
    0.18
    Letters
    0.16
    letters
    0.15
     букв
    0.15
     Letters
    0.15
     अक्ष
    0.14
    _letter
    0.14
     LETTER
    0.14
    -letter
    0.13
    Activations Density 0.005%

    No Known Activations