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. 65074
    Prev
    Next
    INDEX
    Explanations

    AR

    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
    所在地
    -0.08
     understatement
    -0.08
     gevolgen
    -0.08
     consequências
    -0.07
     Garcia
    -0.07
    URIComponent
    -0.07
     outwe
    -0.07
    soever
    -0.07
    -site
    -0.07
    辛
    -0.07
    POSITIVE LOGITS
     Assistant
    0.10
    Assistant
    0.09
    tap
    0.08
     деб
    0.08
    .tap
    0.08
    Feat
    0.08
     demo
    0.07
     Enrollment
    0.07
    Folder
    0.07
     dairy
    0.07
    Activations Density 0.003%

    No Known Activations