© 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. 3-RESID-POST-AA
    11. 2755
    Prev
    Next
    INDEX
    Explanations

    kur

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bal
    -0.09
     преп
    -0.08
     gan
    -0.08
    balances
    -0.08
     balancing
    -0.08
     ebe
    -0.08
     Tamb
    -0.07
     bal
    -0.07
     удар
    -0.07
     vinyl
    -0.07
    POSITIVE LOGITS
    enerate
    0.07
     Mia
    0.07
    zo
    0.07
     sple
    0.07
     சார
    0.07
    _Y
    0.07
     inde
    0.07
    咪
    0.07
     Als
    0.07
     Decide
    0.07
    Activations Density 0.002%

    No Known Activations