© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 18066
    Prev
    Next
    INDEX
    Explanations

    cubes and 3d shapes

    np_max-act-logits · gemini-2.0-flash
    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
    Negative Logits
     newspaper
    -0.13
     Newspaper
    -0.12
     newspapers
    -0.12
    (circle
    -0.11
     Newspapers
    -0.11
     બે
    -0.11
    .circle
    -0.10
     kedua
    -0.10
     જિલ્લા
    -0.10
     inning
    -0.10
    POSITIVE LOGITS
     voxel
    0.27
     cube
    0.24
    Voxel
    0.24
     tetra
    0.23
     vox
    0.23
    Cube
    0.23
    _cube
    0.23
     sphere
    0.23
     volum
    0.22
     Cube
    0.22
    Activations Density 0.313%

    No Known Activations