© 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. 91776
    Prev
    Next
    INDEX
    Explanations

    geometry, parallel and perpendicular lines

    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
     combined
    -0.09
     concaten
    -0.07
    .If
    -0.07
    ovic
    -0.07
    Combined
    -0.07
    .combine
    -0.07
     Combined
    -0.07
     отдельных
    -0.07
     may
    -0.07
     روز
    -0.07
    POSITIVE LOGITS
     معه
    0.10
     친구
    0.10
     respecto
    0.09
    伙伴
    0.09
    _PCM
    0.09
     thereto
    0.09
     ему
    0.09
    Neben
    0.09
    genoten
    0.09
     साथी
    0.09
    Activations Density 0.024%

    No Known Activations