© 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. 49605
    Prev
    Next
    INDEX
    Explanations

    Repetition in another language

    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
     перев
    -0.08
    atua
    -0.07
     redis
    -0.07
    -0.07
     ap
    -0.07
    īta
    -0.07
    án
    -0.07
    丈
    -0.07
     buffalo
    -0.07
     BOX
    -0.07
    POSITIVE LOGITS
    торы
    0.10
    tout
    0.09
    торов
    0.09
    рат
    0.08
    тора
    0.08
    tor
    0.08
    rnd
    0.08
     rinse
    0.08
    r
    0.08
    тори
    0.08
    Activations Density 0.001%
    No Known Activations