© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 95162
    Prev
    Next
    INDEX
    Explanations

    markdown

    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
     Rolls
    -0.08
     Bureau
    -0.08
     glimpse
    -0.08
    INCT
    -0.08
     dma
    -0.08
     race
    -0.08
     Hyundai
    -0.07
     perigos
    -0.07
     GDP
    -0.07
     UDP
    -0.07
    POSITIVE LOGITS
    markdown
    0.12
    Markdown
    0.11
     Markdown
    0.11
     markdown
    0.10
    �
    0.08
     berc
    0.08
     markup
    0.08
    -cli
    0.08
    PDF
    0.08
     작성
    0.07
    Activations Density 0.005%

    No Known Activations