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. 49244
    Prev
    Next
    INDEX
    Explanations

    mathematical sequences

    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
     PREFIX
    -0.08
    Kurz
    -0.08
     Modell
    -0.08
     Sug
    -0.08
     modellen
    -0.07
     slipping
    -0.07
     pups
    -0.07
     Wandel
    -0.07
     превыш
    -0.07
     slope
    -0.07
    POSITIVE LOGITS
     Surf
    0.09
    appointments
    0.08
    cação
    0.08
    Surf
    0.08
     disconnected
    0.08
     appointments
    0.08
    арына
    0.08
     recurring
    0.08
    éry
    0.08
    िक्ष
    0.08
    Activations Density 0.047%

    No Known Activations