© 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. 19-RESID-POST-AA
    11. 103208
    Prev
    Next
    INDEX
    Explanations

    Square shape/term

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    тыру
    -0.10
     molestie
    -0.08
     dropped
    -0.08
    처
    -0.08
     häufiger
    -0.08
     ухуд
    -0.08
     DROP
    -0.08
     Erw
    -0.08
     измен
    -0.08
    __('
    -0.08
    POSITIVE LOGITS
    204
    0.11
    108
    0.11
     square
    0.10
    102
    0.10
    -square
    0.09
    409
    0.09
    192
    0.09
     Canva
    0.09
     квадрат
    0.09
     Square
    0.09
    Activations Density 0.021%

    No Known Activations