© 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. 23-RESID-POST-AA
    11. 48831
    Prev
    Next
    INDEX
    Explanations

    say ода

    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
     Caring
    -0.08
    endelea
    -0.08
     ماده
    -0.08
    iums
    -0.08
    finity
    -0.08
     toezicht
    -0.08
    эм
    -0.08
    ანია
    -0.08
    хэг
    -0.07
    nader
    -0.07
    POSITIVE LOGITS
    ода
    0.18
    оду
    0.12
    оза
    0.11
     guess
    0.09
    dates
    0.08
    ожу
    0.08
     dates
    0.08
    рата
    0.08
    oda
    0.08
    guess
    0.08
    Activations Density 0.002%

    No Known Activations