© 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. 108213
    Prev
    Next
    INDEX
    Explanations

    distances in miles

    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
    .slot
    -0.09
    Throwable
    -0.09
    =format
    -0.08
    afx
    -0.08
     throne
    -0.08
     donnera
    -0.08
    plate
    -0.08
    χα
    -0.08
     infantiles
    -0.08
     plastics
    -0.08
    POSITIVE LOGITS
     distances
    0.20
     दूरी
    0.20
    距离
    0.20
     distance
    0.19
     расстоя
    0.19
    .distance
    0.18
     distancia
    0.18
     Distance
    0.18
    _distance
    0.18
    Distance
    0.17
    Activations Density 0.041%

    No Known Activations