© 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. 48824
    Prev
    Next
    INDEX
    Explanations

    say numbers

    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
     Agoda
    -0.10
     Expedia
    -0.10
     travelers
    -0.10
     traveler
    -0.10
    游客
    -0.10
     Tourism
    -0.10
    旅游
    -0.10
     travellers
    -0.09
     viajeros
    -0.09
     Travelocity
    -0.09
    POSITIVE LOGITS
     squat
    0.22
    重量
    0.21
     lifting
    0.21
     lifts
    0.21
    lifting
    0.20
     bodybuilding
    0.20
     levantamento
    0.20
     वजन
    0.19
     lift
    0.19
     bench
    0.19
    Activations Density 0.072%

    No Known Activations