© 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. 31290
    Prev
    Next
    INDEX
    Explanations

    additive

    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
     folle
    -0.08
     Maid
    -0.08
     hake
    -0.08
     σημ
    -0.08
    Vil
    -0.08
     kee
    -0.08
    握
    -0.08
    eser
    -0.07
     Vid
    -0.07
     maneuver
    -0.07
    POSITIVE LOGITS
     ilus
    0.08
     Calder
    0.08
    AN
    0.08
    ும்ப
    0.07
    ition
    0.07
     scap
    0.07
     interchangeable
    0.07
     населения
    0.07
     equality
    0.07
    ுக்
    0.07
    Activations Density 0.003%

    No Known Activations