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

    Neuronpedia

    APICircuit 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. 60808
    Prev
    Next
    INDEX
    Explanations

    am

    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
    Han
    -0.09
     Han
    -0.08
    laget
    -0.08
     Mom
    -0.08
     brag
    -0.08
     lob
    -0.08
     Fell
    -0.07
     molest
    -0.07
     Lap
    -0.07
    ส
    -0.07
    POSITIVE LOGITS
     Chad
    0.08
    glass
    0.08
     traction
    0.08
    ിരുന്നു
    0.07
     chloride
    0.07
     intimately
    0.07
    否
    0.07
    imoto
    0.07
    ROM
    0.07
    ement
    0.07
    Activations Density 0.069%

    No Known Activations