© 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. 78120
    Prev
    Next
    INDEX
    Explanations

    OpenCV code

    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
     Lie
    -0.09
     Sustainable
    -0.09
    wealth
    -0.09
     sockaddr
    -0.08
     sustainable
    -0.08
     Immobilien
    -0.08
     woven
    -0.08
     infinit
    -0.08
    .Values
    -0.08
     rejo
    -0.08
    POSITIVE LOGITS
     grayscale
    0.13
     whiten
    0.11
     preprocessing
    0.10
    _gray
    0.10
    Noise
    0.09
     preprocess
    0.09
    .gray
    0.09
     OCR
    0.09
    Captcha
    0.09
     limpiar
    0.09
    Activations Density 0.007%

    No Known Activations