© 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 EvalsExportsinterp-engineNEWAPI 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. 50914
    Prev
    Next
    INDEX
    Explanations

    Japanese 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
    λαδή
    -0.09
    ು
    -0.09
    ийм
    -0.09
    ା
    -0.09
    ા
    -0.09
    ેગ
    -0.08
    ிய
    -0.08
    ා
    -0.08
    ୍
    -0.08
    երով
    -0.08
    POSITIVE LOGITS
    ぽ
    0.12
    ぷん
    0.11
    �
    0.11
    �
    0.11
    キー
    0.10
    ぷ
    0.10
    �়ে
    0.09
    �ಿ
    0.09
    ちゃ
    0.09
    �
    0.09
    Activations Density 0.001%

    No Known Activations