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. 12150
    Prev
    Next
    INDEX
    Explanations

    dk

    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
     étude
    -0.08
     Xml
    -0.08
     Paper
    -0.07
     receptive
    -0.07
     Iranian
    -0.07
     مخاط
    -0.07
     mẫu
    -0.07
    납
    -0.07
     helpless
    -0.07
     sufrido
    -0.07
    POSITIVE LOGITS
    ports
    0.09
    ROM
    0.09
     PTA
    0.08
    _ports
    0.08
     ports
    0.08
    /javase
    0.08
    rom
    0.08
     ontwikk
    0.08
     Sommer
    0.08
    -ren
    0.08
    Activations Density 0.005%

    No Known Activations