© 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. 69469
    Prev
    Next
    INDEX
    Explanations

    sales

    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
     early
    -0.09
     فار
    -0.08
     Early
    -0.08
    ền
    -0.08
     настав
    -0.08
    early
    -0.07
     jardin
    -0.07
     frü
    -0.07
    Early
    -0.07
    маган
    -0.07
    POSITIVE LOGITS
    销量
    0.11
     goodwill
    0.09
     વેચ
    0.09
     ജന
    0.09
    販
    0.09
    销售
    0.09
    商品
    0.08
     ventas
    0.08
     sold
    0.08
    Sold
    0.08
    Activations Density 0.008%

    No Known Activations