© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 129426
    Prev
    Next
    INDEX
    Explanations

    underestimate

    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
    .CH
    -0.08
     star
    -0.07
     course
    -0.07
     torture
    -0.07
     unfortunate
    -0.07
    销
    -0.07
     produz
    -0.07
    .Tuple
    -0.07
     ér
    -0.07
     convol
    -0.07
    POSITIVE LOGITS
     underestimated
    0.11
     последствия
    0.10
     количества
    0.09
     weitem
    0.09
     underestimate
    0.09
     размера
    0.09
     capitalization
    0.08
    capitalize
    0.08
     размеры
    0.08
     mauris
    0.08
    Activations Density 0.019%

    No Known Activations