© 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. 70562
    Prev
    Next
    INDEX
    Explanations

    tasked

    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
    Kel
    -0.08
    凸
    -0.08
     malin
    -0.07
     prova
    -0.07
    Robot
    -0.07
     ks
    -0.07
     einsch
    -0.07
    .PREFERRED
    -0.07
     verk
    -0.07
     î
    -0.07
    POSITIVE LOGITS
     responsibility
    0.09
     Edwards
    0.08
     responsabilidade
    0.08
     ক্ষেত্রে
    0.08
    TASK
    0.08
    ırı
    0.08
     responsabilidades
    0.08
     Responsibility
    0.07
     nhiệm
    0.07
    ವರ
    0.07
    Activations Density 0.002%

    No Known Activations