© 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. 108575
    Prev
    Next
    INDEX
    Explanations

    Quotations

    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
     predetermined
    -0.08
     chants
    -0.08
     nage
    -0.08
     thro
    -0.07
     없이
    -0.07
     Provincial
    -0.07
     pripr
    -0.07
     reciente
    -0.07
     slurry
    -0.07
     Flyers
    -0.07
    POSITIVE LOGITS
    Este
    0.09
     dictum
    0.08
     উদ্য
    0.08
     Garten
    0.08
    erry
    0.08
    乔
    0.08
     remarked
    0.08
     Chester
    0.08
     Aristotle
    0.07
     সমাজ
    0.07
    Activations Density 0.039%

    No Known Activations