© 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. 19-RESID-POST-AA
    11. 18937
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    np_max-act-logits · gemini-2.0-flash
    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
     thus
    -0.12
     hence
    -0.12
     thereby
    -0.11
     therefore
    -0.11
     dlatego
    -0.11
     поэтому
    -0.11
     ולכן
    -0.11
     sehingga
    -0.11
     daher
    -0.10
    ，因此
    -0.10
    POSITIVE LOGITS
    ‬↵↵
    0.16
    ‌↵↵
    0.15
    ？↵↵
    0.14
    ؟↵↵
    0.14
    ‍↵↵
    0.14
    **↵↵
    0.13
    ]↵↵
    0.13
    】↵↵
    0.13
    *↵↵
    0.13
    　　↵↵
    0.12
    Activations Density 0.042%

    No Known Activations