© 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. 23-RESID-POST-AA
    11. 49237
    Prev
    Next
    INDEX
    Explanations

    Lim

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    اتو
    -0.09
    ÁT
    -0.08
    ुर
    -0.08
     पैदा
    -0.08
    ooled
    -0.08
    šku
    -0.08
     emperor
    -0.08
    ATIC
    -0.08
    ~-~-
    -0.08
     Hiro
    -0.08
    POSITIVE LOGITS
    itation
    0.22
    iting
    0.21
    iter
    0.18
    itez
    0.17
    iteerd
    0.15
    ite
    0.15
    ites
    0.15
    itação
    0.14
    iteren
    0.14
    itações
    0.14
    Activations Density 0.001%

    No Known Activations