© 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. 64354
    Prev
    Next
    INDEX
    Explanations

    logic puzzle

    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
    átil
    -0.09
     rojo
    -0.09
     symbolic
    -0.08
     확보
    -0.08
    .ylabel
    -0.08
     упаков
    -0.08
     разоб
    -0.08
     estimating
    -0.08
     approximate
    -0.08
     subprocess
    -0.08
    POSITIVE LOGITS
    Everyone
    0.12
     بينهم
    0.11
     Everyone
    0.10
     friendships
    0.10
    Announcements
    0.10
    everyone
    0.10
     polite
    0.10
     Broadcast
    0.09
     Greeting
    0.09
     gegense
    0.09
    Activations Density 0.013%

    No Known Activations