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. 76301
    Prev
    Next
    INDEX
    Explanations

    mathematical computations

    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
     رول
    -0.08
    lyn
    -0.08
     রান
    -0.08
     EFT
    -0.08
    (named
    -0.08
     هیواد
    -0.08
    ’effet
    -0.08
     স্ক
    -0.08
    اتې
    -0.08
     namens
    -0.08
    POSITIVE LOGITS
     trách
    0.09
     comparing
    0.08
     competir
    0.08
     competing
    0.08
     disagree
    0.07
     vs
    0.07
    Interactor
    0.07
     equals
    0.07
     comparable
    0.07
     đáp
    0.07
    Activations Density 0.131%

    No Known Activations