© 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. 64557
    Prev
    Next
    INDEX
    Explanations

    yeast

    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
     faculties
    -0.09
    lade
    -0.08
    ిట
    -0.08
    _RDWR
    -0.07
     плат
    -0.07
     оборудования
    -0.07
     male
    -0.07
    ેશ
    -0.07
    elage
    -0.07
    ేష్
    -0.07
    POSITIVE LOGITS
    纠
    0.09
     bikin
    0.08
    经典
    0.08
     ಗೆ
    0.07
     dominance
    0.07
    ($_
    0.07
     regelmatig
    0.07
     clásicos
    0.07
     ഉണ്ട
    0.07
     teveel
    0.07
    Activations Density 0.003%

    No Known Activations