© 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. 68791
    Prev
    Next
    INDEX
    Explanations

    punctuation and conjunctions

    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
    timestamp
    -0.12
    .timestamp
    -0.12
    _timestamp
    -0.12
    Temporal
    -0.11
    .Timestamp
    -0.11
    (timestamp
    -0.11
     timestamp
    -0.11
     yeroo
    -0.11
     tempore
    -0.11
     temporal
    -0.11
    POSITIVE LOGITS
     бир
    0.08
    地点
    0.07
     moch
    0.07
     impressive
    0.07
     interventions
    0.07
     trivial
    0.07
     સ્થળ
    0.07
    0.07
     fairs
    0.07
     penger
    0.07
    Activations Density 0.179%
    No Known Activations