© 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. 11-RESID-POST-AA
    11. 110598
    Prev
    Next
    INDEX
    Explanations

    yearly events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     доступа
    -0.08
    253
    -0.07
    ched
    -0.07
     Ответ
    -0.07
    259
    -0.07
    тердің
    -0.07
    فت
    -0.07
    thers
    -0.07
     nowhere
    -0.07
    ทั้งหมด
    -0.07
    POSITIVE LOGITS
    마다
    0.12
     сайын
    0.12
     সকালে
    0.10
     מחדש
    0.09
    都会
    0.09
     تقريب
    0.08
     রাতে
    0.08
     anew
    0.08
    istent
    0.08
     recurrent
    0.08
    Activations Density 0.061%

    No Known Activations