© 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. 11-RESID-POST-AA
    11. 114205
    Prev
    Next
    INDEX
    Explanations

    PETSc library

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Emoji
    -0.13
    emoji
    -0.11
     emoji
    -0.11
     Emoji
    -0.10
    分享
    -0.10
     emot
    -0.10
     emotional
    -0.10
     autoplay
    -0.10
     safari
    -0.10
     celebration
    -0.10
    POSITIVE LOGITS
     Petsc
    0.15
     vtk
    0.12
     diagonal
    0.12
    Solver
    0.12
     solver
    0.12
    Diagonal
    0.11
    solver
    0.11
     MPI
    0.11
     diag
    0.11
     ierr
    0.11
    Activations Density 0.012%

    No Known Activations