© 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. 15-RESID-POST-AA
    11. 16260
    Prev
    Next
    INDEX
    Explanations

    upper

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الفرد
    -0.07
     timings
    -0.07
    persoon
    -0.07
     fonctions
    -0.07
    你好
    -0.07
     durations
    -0.07
    _function
    -0.07
    tem
    -0.07
     repl
    -0.07
     проч
    -0.07
    POSITIVE LOGITS
     వరకు
    0.11
     генә
    0.10
     മാത്രം
    0.10
     మాత్రమే
    0.10
     മുതൽ
    0.10
     portion
    0.10
     સુધી
    0.10
     ಮಾತ್ರ
    0.10
     ғана
    0.09
    까
    0.09
    Activations Density 0.005%

    No Known Activations