© 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. 16394
    Prev
    Next
    INDEX
    Explanations

    not

    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
     επικ
    -0.08
    라
    -0.08
     furthermore
    -0.08
     expedite
    -0.08
     structure
    -0.08
    liwo
    -0.08
     olsa
    -0.07
     ezigbo
    -0.07
     véritable
    -0.07
     overarching
    -0.07
    POSITIVE LOGITS
     принад
    0.11
     belonged
    0.10
     pertenc
    0.10
    охож
    0.10
     kuulu
    0.10
     belonging
    0.09
    -owned
    0.09
    belongs
    0.09
     المجموعة
    0.09
     вош
    0.09
    Activations Density 0.013%

    No Known Activations