© 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. 70670
    Prev
    Next
    INDEX
    Explanations

    galaxies and math notation

    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
     bracelet
    -0.09
     sanitaire
    -0.08
     gson
    -0.08
     Crossword
    -0.08
     ETA
    -0.08
     gah
    -0.08
     ")"
    -0.08
    reda
    -0.08
     пов
    -0.08
     calculator
    -0.08
    POSITIVE LOGITS
     galaxies
    0.17
     galaxy
    0.15
     outskirts
    0.11
    Galaxy
    0.10
     Navarro
    0.10
     mergers
    0.10
     elliptical
    0.10
     halos
    0.09
     elongated
    0.09
     pristine
    0.09
    Activations Density 0.005%

    No Known Activations