© 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. 50545
    Prev
    Next
    INDEX
    Explanations

    Non-English words

    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
     CWE
    -0.07
    -type
    -0.07
     property's
    -0.07
    .social
    -0.07
    55
    -0.07
    итель
    -0.07
    Aux
    -0.07
    31
    -0.07
    43
    -0.07
     কাউ
    -0.07
    POSITIVE LOGITS
    рован
    0.11
    ру
    0.10
    الف
    0.09
    ровать
    0.09
    пред
    0.09
    умент
    0.09
    ड
    0.09
    õttu
    0.08
     portátil
    0.08
    ટ
    0.08
    Activations Density 0.002%

    No Known Activations