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. 23-RESID-POST-AA
    6. 98146
    Prev
    Next
    INDEX
    Explanations

    Camera sensors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eloitte
    -0.09
    Honda
    -0.09
    MISSION
    -0.08
    cached
    -0.08
    Marvel
    -0.08
    �ిల్లీ
    -0.08
    acking
    -0.08
    ajajo
    -0.08
    anym
    -0.08
    Fare
    -0.08
    POSITIVE LOGITS
     ip
    0.09
     स्ट्र
    0.08
     '/',
    0.08
     esc
    0.08
     Esc
    0.08
     ESC
    0.07
     nucleus
    0.07
     medium
    0.07
     pp
    0.07
     getters
    0.07
    Activations Density 0.001%

    No Known Activations