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. 53193
    Prev
    Next
    INDEX
    Explanations

    Edinburgh

    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
     عن
    -0.08
     jud
    -0.07
    ादी
    -0.07
     Eddy
    -0.07
    Glad
    -0.07
     ד
    -0.07
    दी
    -0.07
    ряд
    -0.07
     abr
    -0.07
    argest
    -0.07
    POSITIVE LOGITS
     Decorating
    0.08
    Sandbox
    0.08
     COMP
    0.08
     Andreas
    0.07
     chambers
    0.07
     Moss
    0.07
    BOUND
    0.07
    verein
    0.07
     compliments
    0.07
    олож
    0.07
    Activations Density 0.004%

    No Known Activations