© 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. 11-RESID-POST-AA
    11. 69416
    Prev
    Next
    INDEX
    Explanations

    Fish types

    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
     lavish
    -0.08
     ग्र
    -0.07
     scu
    -0.07
     категор
    -0.07
    iad
    -0.07
     liên
    -0.07
     rail
    -0.07
     categorical
    -0.07
     aceler
    -0.07
     pribadi
    -0.07
    POSITIVE LOGITS
    Cro
    0.09
     Mercy
    0.09
    Ced
    0.09
     Cro
    0.09
     Maggie
    0.08
     Ch
    0.08
     shores
    0.08
     Gallagher
    0.08
     Margaret
    0.08
    eroo
    0.08
    Activations Density 0.004%

    No Known Activations