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. 30744
    Prev
    Next
    INDEX
    Explanations

    quad

    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
    ardin
    -0.07
     Me
    -0.07
     Metallic
    -0.07
    Healthcare
    -0.07
     Gaz
    -0.07
     pasan
    -0.07
     guests
    -0.07
    Gaz
    -0.07
    مال
    -0.07
    ोजना
    -0.07
    POSITIVE LOGITS
    bringen
    0.08
     distinta
    0.08
     (/
    0.07
    ioxid
    0.07
     Week
    0.07
    රු
    0.07
     foll
    0.07
    .User
    0.07
    	put
    0.07
    ございます
    0.07
    Activations Density 0.001%

    No Known Activations