© 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. 19-RESID-POST-AA
    11. 18906
    Prev
    Next
    INDEX
    Explanations

    plus sign

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     отрим
    -0.10
     đỏ
    -0.08
    했다고
    -0.08
     атрым
    -0.08
    得到
    -0.08
     булды
    -0.08
     получить
    -0.07
    <len
    -0.07
     Sar
    -0.07
    _SWAP
    -0.07
    POSITIVE LOGITS
    /
↵
    0.09
    ()];↵
    0.09
    /.↵
    0.09
     acronym
    0.09
    cors
    0.08
    /↵//
    0.08
    /↵
    0.08
    `;↵
    0.08
    ];↵
    0.08
    /';↵
    0.08
    Activations Density 0.002%

    No Known Activations