© 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. 63676
    Prev
    Next
    INDEX
    Explanations

    .

    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
     bảo
    -0.08
     promov
    -0.08
    ounen
    -0.07
    ucleotide
    -0.07
    qt
    -0.07
    stemming
    -0.07
     promoción
    -0.07
     conducción
    -0.07
     Reven
    -0.07
     revenus
    -0.07
    POSITIVE LOGITS
    108
    0.08
     Photographer
    0.08
    case
    0.07
     gert
    0.07
     вос
    0.07
     alveg
    0.07
     photographer
    0.07
     inget
    0.07
     firearms
    0.07
     વ
    0.07
    Activations Density 0.000%

    No Known Activations