© 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. 26313
    Prev
    Next
    INDEX
    Explanations

    to

    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
    esters
    -0.07
     चर्च
    -0.07
     SHOP
    -0.07
    enting
    -0.07
    weak
    -0.07
    ैं
    -0.07
     graphs
    -0.07
     avere
    -0.07
     инструмент
    -0.07
    forcing
    -0.07
    POSITIVE LOGITS
     wollte
    0.08
     Penis
    0.08
     lei
    0.08
     Lei
    0.08
     cared
    0.08
     말했다
    0.08
    سے
    0.08
    .personal
    0.08
     adrenaline
    0.08
     weiss
    0.08
    Activations Density 0.001%

    No Known Activations