© 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. 108668
    Prev
    Next
    INDEX
    Explanations

    code-related

    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
    Launcher
    -0.07
    Deployment
    -0.07
     deployment
    -0.07
     blister
    -0.07
     shut
    -0.07
     Laval
    -0.07
    kehr
    -0.07
     Beschäft
    -0.07
    ников
    -0.07
     lide
    -0.07
    POSITIVE LOGITS
     `,↵
    0.08
    (enum
    0.08
    =test
    0.08
     abb
    0.08
    _orig
    0.08
     vrijblij
    0.07
    _pas
    0.07
     datings
    0.07
     aang
    0.07
    นำ
    0.07
    Activations Density 0.000%

    No Known Activations