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. 43917
    Prev
    Next
    INDEX
    Explanations

    Abstraction in programming

    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
     привет
    -0.07
     xin
    -0.07
     chili
    -0.07
     �
    -0.07
     prévue
    -0.07
     stip
    -0.07
     stir
    -0.07
     rumored
    -0.07
     京
    -0.07
    prime
    -0.07
    POSITIVE LOGITS
     abstraction
    0.10
     away
    0.10
     abstra
    0.10
     سطح
    0.09
    .Abstract
    0.09
     수준
    0.09
     المستوى
    0.08
     couches
    0.08
    тесь
    0.08
    .Obj
    0.08
    Activations Density 0.004%

    No Known Activations