© 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. 11-RESID-POST-AA
    11. 95913
    Prev
    Next
    INDEX
    Explanations

    Stop words and auxiliaries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -containing
    -0.08
     contours
    -0.08
     அதன்
    -0.08
     conjug
    -0.08
    년도
    -0.07
    Ihr
    -0.07
    _SUPPORT
    -0.07
    Contours
    -0.07
     京都
    -0.07
    νης
    -0.07
    POSITIVE LOGITS
     overly
    0.11
     слишком
    0.10
     too
    0.09
    too
    0.08
    忽
    0.08
    anje
    0.08
     demasiado
    0.08
     insufficient
    0.08
     demasi
    0.08
    ajah
    0.08
    Activations Density 0.118%

    No Known Activations