© 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. 97533
    Prev
    Next
    INDEX
    Explanations

    zas

    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
    usut
    -0.09
     Mandel
    -0.09
    ൂട്ട
    -0.08
     Debian
    -0.08
     Bridal
    -0.08
    əyə
    -0.07
    াকে
    -0.07
    ്ക്ക
    -0.07
    єн
    -0.07
    ার
    -0.07
    POSITIVE LOGITS
    z
    0.21
    zés
    0.11
    zí
    0.10
    zif
    0.10
    zó
    0.10
    zano
    0.10
    ζ
    0.10
    zuje
    0.10
    zere
    0.09
    zu
    0.09
    Activations Density 0.001%

    No Known Activations