© 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. 7-RESID-POST-AA
    11. 719
    Prev
    Next
    INDEX
    Explanations

    novelty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    梦
    -0.08
    үм
    -0.08
     resolves
    -0.07
     resolución
    -0.07
    မ
    -0.07
     indicative
    -0.07
     Mari
    -0.07
     epis
    -0.07
     hypot
    -0.07
    've
    -0.07
    POSITIVE LOGITS
     novelty
    0.10
     amuse
    0.08
     intrigue
    0.08
     ввод
    0.08
     کند
    0.08
     dare
    0.07
     alloys
    0.07
     alloy
    0.07
    lessness
    0.07
     doit
    0.07
    Activations Density 0.006%

    No Known Activations