© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 49968
    Prev
    Next
    INDEX
    Explanations

    master's degree

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     collège
    -0.10
     batt
    -0.08
     major
    -0.08
    벤
    -0.08
     crim
    -0.08
    ^-
    -0.07
     부족
    -0.07
    .major
    -0.07
     '-',
    -0.07
    وريا
    -0.07
    POSITIVE LOGITS
     master's
    0.23
     Master
    0.23
     Master's
    0.22
    Master
    0.21
     master
    0.21
    .Master
    0.21
     Masters
    0.21
     masters
    0.20
    Masters
    0.19
    _master
    0.19
    Activations Density 0.044%

    No Known Activations