Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 55931
    Prev
    Next
    INDEX
    Explanations

    cross product

    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
    отеки
    -0.09
    schemas
    -0.08
     yhdessä
    -0.08
     مجتمع
    -0.08
     Мас
    -0.08
    _DURATION
    -0.08
     حلق
    -0.08
    ుతో
    -0.08
     betrieben
    -0.08
    �్త
    -0.08
    POSITIVE LOGITS
     manually
    0.09
    �
    0.09
     perpendicular
    0.08
    curl
    0.08
     curls
    0.08
     curl
    0.08
     vector
    0.08
    атков
    0.08
     skew
    0.08
     auxiliar
    0.07
    Activations Density 0.013%

    No Known Activations