© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 49903
    Prev
    Next
    INDEX
    Explanations

    оряд

    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
    uisce
    -0.10
    τηση
    -0.09
    ụtara
    -0.08
    imenti
    -0.08
    енная
    -0.08
     auf
    -0.08
    იძლია
    -0.08
    θει
    -0.08
    τήσει
    -0.08
    utamente
    -0.08
    POSITIVE LOGITS
    ли
    0.10
    лива
    0.10
    ician
    0.08
    чиков
    0.08
    ьд
    0.08
    арц
    0.08
    лини
    0.08
     Squadron
    0.07
     Sama
    0.07
    acist
    0.07
    Activations Density 0.002%

    No Known Activations