© 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. 23-RESID-POST-AA
    11. 49186
    Prev
    Next
    INDEX
    Explanations

    coordination

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     муч
    -0.10
     Mass
    -0.08
    .Volume
    -0.08
    -Day
    -0.08
     Clean
    -0.08
    .mass
    -0.08
     पदार्थ
    -0.08
    curve
    -0.08
     vandaag
    -0.08
     substance
    -0.08
    POSITIVE LOGITS
     coordination
    0.23
     coordinación
    0.22
     coordinated
    0.22
     Coordination
    0.21
     coordinating
    0.20
     coordin
    0.19
    Coord
    0.19
     coord
    0.19
     Coordin
    0.18
    coord
    0.18
    Activations Density 0.014%

    No Known Activations