© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 68861
    Prev
    Next
    INDEX
    Explanations

    want

    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
    之外
    -0.09
     boasting
    -0.09
     داشته
    -0.08
     battles
    -0.08
    ਹਿਲ
    -0.08
     이후
    -0.08
     đẹp
    -0.08
    .dispose
    -0.08
     boasts
    -0.08
    uvu
    -0.08
    POSITIVE LOGITS
     presumably
    0.10
     assistance
    0.09
     basically
    0.09
     graag
    0.09
     yönelik
    0.09
     GPT
    0.09
     مني
    0.09
     চান
    0.09
     waarschijnlijk
    0.08
     Basically
    0.08
    Activations Density 0.051%

    No Known Activations