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. 11-RESID-POST-AA
    6. 58573
    Prev
    Next
    INDEX
    Explanations

    parabola

    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
     Jee
    -0.07
    Enjoy
    -0.07
     biode
    -0.07
    critic
    -0.07
    Advantages
    -0.07
     Pflege
    -0.07
     bowel
    -0.07
     मुकाब
    -0.07
     walnuts
    -0.07
     doubts
    -0.07
    POSITIVE LOGITS
     yuz
    0.09
     धन
    0.08
     centred
    0.08
     τρα
    0.08
     sidan
    0.08
     klasik
    0.08
     ngok
    0.08
     laus
    0.08
     clásica
    0.08
     yüzden
    0.08
    Activations Density 0.016%

    No Known Activations