© 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. 49488
    Prev
    Next
    INDEX
    Explanations

    Russian text

    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
     terem
    -0.08
     ori
    -0.08
    oles
    -0.08
    oden
    -0.08
    acje
    -0.08
    ole
    -0.08
    ಂಟ
    -0.08
    zg
    -0.08
    әд
    -0.07
    نوك
    -0.07
    POSITIVE LOGITS
    жение
    0.11
    жается
    0.11
    га
    0.11
    ваем
    0.10
    жения
    0.10
    кая
    0.09
    ження
    0.09
    пания
    0.08
    жи
    0.08
    вайте
    0.08
    Activations Density 0.002%

    No Known Activations