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. 112813
    Prev
    Next
    INDEX
    Explanations

    SOC

    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
     Belle
    -0.08
     Shelley
    -0.07
     denom
    -0.07
     Expand
    -0.07
     nam
    -0.07
    expand
    -0.07
     Spiel
    -0.07
     JAV
    -0.07
     cascade
    -0.07
     Bacon
    -0.07
    POSITIVE LOGITS
     appreh
    0.09
     кругл
    0.08
     най
    0.08
    リア
    0.08
     vaardigheden
    0.08
     కి
    0.08
    най
    0.08
     draaien
    0.07
    год
    0.07
     staffed
    0.07
    Activations Density 0.003%

    No Known Activations