© 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. 54613
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    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
     flatter
    -0.08
    观点
    -0.08
    .collections
    -0.07
     لس
    -0.07
     judging
    -0.07
    ిణ
    -0.07
     réalisée
    -0.07
    τυ
    -0.07
     approachable
    -0.07
     akkurat
    -0.07
    POSITIVE LOGITS
     Sust
    0.08
     encerr
    0.08
     Slow
    0.08
     crear
    0.08
     comando
    0.08
     initi
    0.08
     Initi
    0.07
    Crear
    0.07
     metavar
    0.07
     thunk
    0.07
    Activations Density 0.001%

    No Known Activations