© 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. 50945
    Prev
    Next
    INDEX
    Explanations

    Two character foreign 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
     svm
    -0.08
    Bk
    -0.07
    irhi
    -0.07
     tsev
    -0.07
     编
    -0.07
    chrift
    -0.07
     vermo
    -0.07
    สล็อต
    -0.07
    vom
    -0.07
    thet
    -0.07
    POSITIVE LOGITS
    딩
    0.12
    يج
    0.09
    adden
    0.09
     hø
    0.08
    ジ
    0.08
    �
    0.08
    дау
    0.08
    ーデ
    0.08
     gó
    0.08
    గ్గ
    0.08
    Activations Density 0.001%

    No Known Activations