© 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. 18684
    Prev
    Next
    INDEX
    Explanations

    hope

    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
    ®.
    -0.10
     but
    -0.09
    ().
    -0.09
    typename
    -0.09
    /.↵↵
    -0.09
    >.
    -0.08
     We're
    -0.08
    .They
    -0.08
     چیست
    -0.08
    -type
    -0.08
    POSITIVE LOGITS
    能够
    0.18
    能
    0.17
    可以
    0.17
     بتوان
    0.16
    通过
    0.14
    它
    0.14
    大家
    0.13
    你
    0.13
    这些
    0.13
    有
    0.13
    Activations Density 0.002%

    No Known Activations