© 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. 16629
    Prev
    Next
    INDEX
    Explanations

    essentially

    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
     realistic
    -0.08
    helele
    -0.08
     dapat
    -0.08
     తో
    -0.07
    óis
    -0.07
    ènement
    -0.07
    不能
    -0.07
     pristine
    -0.07
     ngay
    -0.07
     ✅
    -0.07
    POSITIVE LOGITS
     essentially
    0.17
     Essentially
    0.16
     essentiellement
    0.15
     basically
    0.15
     boils
    0.13
     fundamentally
    0.13
    ，就是
    0.12
     Basically
    0.12
     largely
    0.12
     결국
    0.12
    Activations Density 0.059%

    No Known Activations