© 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. 110987
    Prev
    Next
    INDEX
    Explanations

    begins

    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
     ペ
    -0.08
    ifl
    -0.08
     대해
    -0.08
    lose
    -0.08
    //'
    -0.08
     Kolleg
    -0.08
     대해서
    -0.08
     sulit
    -0.07
    >[↵
    -0.07
    assembled
    -0.07
    POSITIVE LOGITS
     groundwork
    0.12
     থেকেই
    0.11
     começar
    0.11
     começo
    0.11
     começa
    0.11
     தொட
    0.10
     শুরু
    0.10
    基础
    0.10
     البداية
    0.10
     kezd
    0.10
    Activations Density 0.034%

    No Known Activations