© 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. 15-RESID-POST-AA
    11. 16675
    Prev
    Next
    INDEX
    Explanations

    Mathematics

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     һәм
    -0.09
     lector
    -0.09
     cheann
    -0.08
    ammar
    -0.08
     masani
    -0.08
    玖玖
    -0.08
    лап
    -0.08
    റും
    -0.08
    ių
    -0.08
    Esk
    -0.08
    POSITIVE LOGITS
     mathem
    0.11
     matemática
    0.09
     matemat
    0.09
     matem
    0.09
     mathematical
    0.09
     !=
    0.08
     formal
    0.08
    <any
    0.08
     mathematics
    0.08
     via
    0.08
    Activations Density 0.168%

    No Known Activations