© 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. 113115
    Prev
    Next
    INDEX
    Explanations

    Neighborhoods

    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
     lihat
    -0.08
     설정
    -0.08
    (format
    -0.08
     시스템
    -0.08
     आँख
    -0.08
    (sizeof
    -0.08
     Tournament
    -0.08
    .API
    -0.08
     Format
    -0.08
     Sujet
    -0.08
    POSITIVE LOGITS
     bairros
    0.18
     suburbs
    0.17
     neighborhoods
    0.17
     bairro
    0.15
     suburb
    0.15
     quartier
    0.14
     quartiers
    0.14
     districts
    0.14
     neighborhood
    0.13
     مناطق
    0.13
    Activations Density 0.114%

    No Known Activations