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. 58710
    Prev
    Next
    INDEX
    Explanations

    Reflections and bouncing

    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
    .params
    -0.08
     epidemi
    -0.08
    params
    -0.07
     smokers
    -0.07
    pg
    -0.07
     worms
    -0.07
     succ
    -0.07
     Params
    -0.07
     Slowly
    -0.07
    employees
    -0.07
    POSITIVE LOGITS
     boundary
    0.10
    _boundary
    0.10
     bounce
    0.09
    boundary
    0.09
    泽
    0.09
     boundaries
    0.09
     reflections
    0.09
    Boundary
    0.09
    Reflection
    0.09
     réflex
    0.09
    Activations Density 0.008%

    No Known Activations