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. 53181
    Prev
    Next
    INDEX
    Explanations

    color theory

    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
     laste
    -0.08
    财
    -0.08
     cint
    -0.08
     statue
    -0.07
     Rome
    -0.07
    Rome
    -0.07
    忍
    -0.07
     Chapel
    -0.07
    纽
    -0.07
    无人
    -0.07
    POSITIVE LOGITS
     შეს
    0.09
     variants
    0.09
     לער
    0.09
    Brightness
    0.09
    GRAY
    0.09
     modifiers
    0.08
     imperfections
    0.08
    contrast
    0.08
     MAG
    0.08
     ಮಟ್ಟ
    0.08
    Activations Density 0.005%

    No Known Activations