Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 65101
    Prev
    Next
    INDEX
    Explanations

    probability problems

    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
     added
    -0.08
     graphene
    -0.08
     method
    -0.07
     shaders
    -0.07
     geometric
    -0.07
     brochures
    -0.07
     brochure
    -0.07
     python
    -0.07
     href
    -0.07
     providing
    -0.07
    POSITIVE LOGITS
     erfolgreichen
    0.10
    Successful
    0.10
     erfolgreiche
    0.10
    successful
    0.10
     instantaneous
    0.09
     Probability
    0.09
     surviving
    0.09
     успеш
    0.09
     Survival
    0.09
     Successful
    0.09
    Activations Density 0.018%

    No Known Activations