© 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. 94839
    Prev
    Next
    INDEX
    Explanations

    Math equations

    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
    同志
    -0.09
    cmp
    -0.08
    prit
    -0.08
     Atendimento
    -0.08
     dég
    -0.08
    atian
    -0.08
    endimento
    -0.08
     assunto
    -0.07
    ')}}</
    -0.07
     proiz
    -0.07
    POSITIVE LOGITS
     reversing
    0.08
     invers
    0.08
     ratios
    0.08
    저
    0.08
    ора
    0.08
     схем
    0.08
     decreasing
    0.08
     succeeding
    0.07
     ficando
    0.07
     powers
    0.07
    Activations Density 0.054%

    No Known Activations