© 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. 49572
    Prev
    Next
    INDEX
    Explanations

    cell

    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
     formación
    -0.09
    形成
    -0.08
    Form
    -0.08
     formazione
    -0.08
     forman
    -0.08
     formação
    -0.08
    .form
    -0.08
    .Form
    -0.08
     COMP
    -0.07
     Form
    -0.07
    POSITIVE LOGITS
     cell
    0.14
    cell
    0.13
     galvan
    0.13
    _cell
    0.13
     Dani
    0.12
     cells
    0.12
    cells
    0.12
    gal
    0.12
    -cell
    0.12
    (cell
    0.12
    Activations Density 0.006%

    No Known Activations