© 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. 99632
    Prev
    Next
    INDEX
    Explanations

    $ and

    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
     bich
    -0.08
    �
    -0.07
     slij
    -0.07
    _LAYOUT
    -0.07
     Bing
    -0.07
     Dairy
    -0.07
     lade
    -0.07
     sar
    -0.07
     pict
    -0.07
    xtap
    -0.07
    POSITIVE LOGITS
    לי
    0.09
    Strike
    0.08
     publicación
    0.08
     dozens
    0.08
    voire
    0.08
     he'll
    0.08
     honderden
    0.08
    签
    0.08
     المجلس
    0.08
    Testimonials
    0.08
    Activations Density 0.011%

    No Known Activations