© 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. 18525
    Prev
    Next
    INDEX
    Explanations

    Current events

    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
    .Login
    -0.10
    .Http
    -0.10
    ‍ය
    -0.10
    .Url
    -0.10
    .File
    -0.09
    .Date
    -0.09
    ‍යා
    -0.09
     même
    -0.09
    Scroller
    -0.09
    _Init
    -0.09
    POSITIVE LOGITS
     Their
    0.17
     Different
    0.15
     Certain
    0.14
     Those
    0.14
     Its
    0.13
     THEIR
    0.12
     Several
    0.11
     Various
    0.11
     Other
    0.11
     Each
    0.11
    Activations Density 0.109%

    No Known Activations