© 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. 15-RESID-POST-AA
    11. 16509
    Prev
    Next
    INDEX
    Explanations

    Legendre's formula

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ข้อ
    -0.09
     Isabelle
    -0.09
     münasib
    -0.08
     బయ
    -0.08
     миним
    -0.08
     ચોક
    -0.08
    ייט
    -0.08
     específicamente
    -0.08
     крайн
    -0.08
     хүр
    -0.08
    POSITIVE LOGITS
     progressively
    0.10
    -series
    0.10
     successive
    0.10
     cumul
    0.09
     summ
    0.09
     contributions
    0.09
     Layers
    0.08
     series
    0.08
     sum
    0.08
     Contributions
    0.08
    Activations Density 0.005%

    No Known Activations