© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 47952
    Prev
    Next
    INDEX
    Explanations

    Number base calculation

    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
    جهه
    -0.08
    ڏي
    -0.08
     //////
    -0.08
    //$
    -0.08
     письмен
    -0.08
    כת
    -0.08
     digging
    -0.08
     accommodated
    -0.08
     Inggris
    -0.07
    ڏ
    -0.07
    POSITIVE LOGITS
    amele
    0.08
     измен
    0.08
    ucceeded
    0.08
    omegran
    0.07
     oceans
    0.07
    wią
    0.07
    _CHANGED
    0.07
     GMP
    0.07
    ･
    0.07
    tons
    0.07
    Activations Density 0.020%

    No Known Activations