© 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. 22132
    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
     любого
    -0.12
    任何
    -0.11
     any
    -0.11
     qualquer
    -0.11
     orice
    -0.11
     quelcon
    -0.11
     любое
    -0.11
     ഏത
    -0.11
     cualquier
    -0.10
     qualsevol
    -0.10
    POSITIVE LOGITS
     behalve
    0.19
    都
    0.19
     excepto
    0.19
     đều
    0.18
    ，都
    0.17
    都是
    0.16
     except
    0.16
    都有
    0.15
     都
    0.15
    都会
    0.15
    Activations Density 0.137%

    No Known Activations