© 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. 19-RESID-POST-AA
    11. 103395
    Prev
    Next
    INDEX
    Explanations

    Communication

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ýö
    -0.09
     ipele
    -0.08
     pamam
    -0.08
     ī
    -0.08
     ikiwa
    -0.08
    netje
    -0.08
     drwy
    -0.08
    дэр
    -0.08
     MBA
    -0.08
     арга
    -0.08
    POSITIVE LOGITS
     comunicação
    0.08
    Front
    0.08
     comunicación
    0.07
    通信
    0.07
     komunikasi
    0.07
    _coords
    0.07
     communication
    0.07
     comunic
    0.07
    后一
    0.07
     frontier
    0.07
    Activations Density 0.000%

    No Known Activations