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. 112799
    Prev
    Next
    INDEX
    Explanations

    Underlining/Highlighting

    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
    document
    -0.08
    versal
    -0.08
    pagina
    -0.08
    ZR
    -0.07
     document
    -0.07
     Detox
    -0.07
    >();↵↵
    -0.07
     Nhưng
    -0.07
    financial
    -0.07
    untary
    -0.07
    POSITIVE LOGITS
     parentheses
    0.09
     depicted
    0.08
     그림
    0.08
     tils
    0.08
     pound
    0.08
     oks
    0.08
     PEG
    0.08
     мной
    0.08
     चिन
    0.07
     ред
    0.07
    Activations Density 0.016%

    No Known Activations