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. 117593
    Prev
    Next
    INDEX
    Explanations

    genetic/environmental interactions

    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
     swim
    -0.09
    ijska
    -0.08
     Row
    -0.08
    يع
    -0.08
    нати
    -0.08
     rie
    -0.08
     stroom
    -0.07
    mov
    -0.07
    enean
    -0.07
    aná
    -0.07
    POSITIVE LOGITS
     allele
    0.09
     Täter
    0.08
    Spiel
    0.08
     predis
    0.08
    刑
    0.08
     susceptible
    0.08
     نوجوان
    0.08
     الجر
    0.08
     sprink
    0.08
     ಪೊಲೀಸರು
    0.08
    Activations Density 0.006%

    No Known Activations