© 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. 111030
    Prev
    Next
    INDEX
    Explanations

    Code with array indices

    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
    @Api
    -0.09
     skinny
    -0.08
    gev
    -0.08
    drag
    -0.08
    \Form
    -0.08
    lechts
    -0.08
    flu
    -0.07
    ignty
    -0.07
    approx
    -0.07
     vó
    -0.07
    POSITIVE LOGITS
     индекс
    0.13
    cycling
    0.12
     cycling
    0.12
     index
    0.11
    _INDEX
    0.11
    _index
    0.11
    cycled
    0.11
    播放
    0.11
     переключ
    0.11
     Cycling
    0.10
    Activations Density 0.011%

    No Known Activations