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. 120421
    Prev
    Next
    INDEX
    Explanations

    New students

    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
     negligible
    -0.08
    �
    -0.08
    στεί
    -0.07
     comércio
    -0.07
     ceiling
    -0.07
     negative
    -0.07
    -0.07
     finely
    -0.07
     both
    -0.07
    所得
    -0.07
    POSITIVE LOGITS
     newcomers
    0.13
     newcomer
    0.13
     bienvenida
    0.13
     स्वागत
    0.12
    Welcome
    0.12
     Welcome
    0.11
    Bienvenue
    0.11
     newbies
    0.11
     нович
    0.11
     bienvenue
    0.11
    Activations Density 0.060%

    No Known Activations