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. 12100
    Prev
    Next
    INDEX
    Explanations

    security

    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
    	W
    -0.08
     agradecer
    -0.08
     mech
    -0.08
    ulli
    -0.08
     generators
    -0.07
     annul
    -0.07
    	has
    -0.07
     Kurz
    -0.07
    ৰৰ
    -0.07
    ыл
    -0.07
    POSITIVE LOGITS
     gona
    0.08
    อยู่
    0.08
    Greetings
    0.07
    ceral
    0.07
     upbringing
    0.07
     proteção
    0.07
    trado
    0.07
    Age
    0.07
    Nada
    0.07
    icky
    0.07
    Activations Density 0.000%

    No Known Activations