Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 55978
    Prev
    Next
    INDEX
    Explanations

    non-english/mixed language

    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
     nr
    -0.08
     zuverläss
    -0.07
     DIRECT
    -0.07
     ™
    -0.07
     Δ
    -0.07
     SQLite
    -0.07
    USES
    -0.06
    -write
    -0.06
    可靠
    -0.06
     heter
    -0.06
    POSITIVE LOGITS
    (Collections
    0.09
     onboarding
    0.08
    ayi
    0.08
    "});↵
    0.08
    ]};↵
    0.08
    Greetings
    0.08
    }};↵
    0.08
    "));↵
    0.08
    Sorting
    0.08
     בתחום
    0.08
    Activations Density 0.121%

    No Known Activations