© 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. 54805
    Prev
    Next
    INDEX
    Explanations

    single-elimination tournaments

    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
    Invariant
    -0.08
     equival
    -0.08
     "::
    -0.08
    yto
    -0.08
     inteligente
    -0.08
     которым
    -0.07
     preciso
    -0.07
     aute
    -0.07
    ersist
    -0.07
    inox
    -0.07
    POSITIVE LOGITS
     knockout
    0.09
     tournament
    0.09
     tournaments
    0.08
     pyramid
    0.08
     மர
    0.08
     மார
    0.08
     playoffs
    0.08
     stagger
    0.08
    跌
    0.08
    梯
    0.08
    Activations Density 0.008%

    No Known Activations