© 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. 19-RESID-POST-AA
    11. 19905
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    'utiliser
    -0.08
     корист
    -0.08
    ấp
    -0.08
    ores
    -0.08
    ạnh
    -0.08
    134
    -0.07
     моб
    -0.07
     нов
    -0.07
    antas
    -0.07
    イズ
    -0.07
    POSITIVE LOGITS
    nection
    0.13
    conciliation
    0.13
    structions
    0.13
     reconc
    0.12
     reconciliation
    0.12
     recon
    0.12
    cil
    0.11
    concile
    0.11
     Recon
    0.11
    hecimento
    0.11
    Activations Density 0.037%

    No Known Activations