© 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. 69318
    Prev
    Next
    INDEX
    Explanations

    bought

    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
     FTC
    -0.08
    .arrow
    -0.08
     THC
    -0.07
     EVO
    -0.07
     demons
    -0.07
    .flutter
    -0.07
     rosa
    -0.07
    anko
    -0.07
     HAC
    -0.07
     বাই
    -0.07
    POSITIVE LOGITS
    编号
    0.09
     stored
    0.08
    ಂಜ
    0.08
     belong
    0.08
    ంజ
    0.08
     franchises
    0.08
     serviced
    0.08
     pastime
    0.08
    Quels
    0.08
     franchise
    0.08
    Activations Density 0.011%

    No Known Activations