© 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. 19998
    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
     যেখানে
    -0.11
     όπου
    -0.10
     որտեղ
    -0.10
     სადაც
    -0.10
     જ્યાં
    -0.10
     kjer
    -0.09
     ambapo
    -0.09
     où
    -0.09
     kurie
    -0.09
     бұл
    -0.09
    POSITIVE LOGITS
     presumably
    0.11
     equals
    0.11
     equal
    0.11
     consists
    0.11
     appears
    0.10
     belongs
    0.10
     moreover
    0.10
     corresponds
    0.10
     albeit
    0.10
     represents
    0.09
    Activations Density 0.039%

    No Known Activations