© 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. 11-RESID-POST-AA
    11. 113300
    Prev
    Next
    INDEX
    Explanations

    chipping or peeling

    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
     jazz
    -0.08
     hone
    -0.07
     நேர
    -0.07
     featured
    -0.07
     prescription
    -0.07
     Nueva
    -0.07
    hora
    -0.07
    .Editor
    -0.07
    analytics
    -0.07
     except
    -0.07
    POSITIVE LOGITS
    裂
    0.12
     brittle
    0.12
    碎
    0.12
     despr
    0.11
     remov
    0.10
     morceaux
    0.10
     떨어
    0.10
    離
    0.10
    Loose
    0.10
     fragmentation
    0.10
    Activations Density 0.029%

    No Known Activations