© 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. 102566
    Prev
    Next
    INDEX
    Explanations

    suffixes

    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
    分
    -0.08
    тк
    -0.08
    ��
    -0.08
    取
    -0.08
    ���
    -0.08
    具体
    -0.08
    整体
    -0.08
    ยัง
    -0.08
    提供
    -0.08
    हरी
    -0.08
    POSITIVE LOGITS
    ness
    0.21
    ly
    0.18
    NESS
    0.15
    erweise
    0.15
    -looking
    0.15
    ities
    0.15
     түрде
    0.15
    ity
    0.15
    ized
    0.15
     રીતે
    0.14
    Activations Density 0.027%

    No Known Activations