© 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. 77894
    Prev
    Next
    INDEX
    Explanations

    containers

    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
     kingdom
    -0.09
     முற
    -0.07
     அழ
    -0.07
     kingdoms
    -0.07
    மை
    -0.07
     scènes
    -0.07
    mid
    -0.07
     geschaffen
    -0.07
    inek
    -0.07
    _CREATE
    -0.07
    POSITIVE LOGITS
     ماء
    0.10
    langen
    0.09
    ette
    0.09
     زيت
    0.08
     groceries
    0.08
     inteira
    0.08
     Lidl
    0.08
     Hond
    0.08
    υμα
    0.08
     baking
    0.08
    Activations Density 0.034%

    No Known Activations