© 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. 26326
    Prev
    Next
    INDEX
    Explanations

    No surprise/disbelief

    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
     indiqué
    -0.09
     basil
    -0.08
     przeci
    -0.08
     idéal
    -0.08
     Invoice
    -0.07
     kerül
    -0.07
     watermark
    -0.07
     allergens
    -0.07
    Eye
    -0.07
     aangegeven
    -0.07
    POSITIVE LOGITS
     surprising
    0.09
     why
    0.09
     unsur
    0.09
     warum
    0.09
     কেন
    0.09
    _EXPECT
    0.09
     disappointing
    0.08
    եդ
    0.08
    �
    0.08
     oček
    0.08
    Activations Density 0.035%

    No Known Activations