© 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. 2625
    Prev
    Next
    INDEX
    Explanations

    天

    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
    умент
    -0.08
     empowered
    -0.08
     Arth
    -0.07
    Txn
    -0.07
    redu
    -0.07
     Merlin
    -0.07
     ดัง
    -0.07
    /dd
    -0.07
     dilig
    -0.07
    adem
    -0.07
    POSITIVE LOGITS
     anth
    0.07
     vietnam
    0.07
    icao
    0.07
     Tak
    0.07
     Stra
    0.07
     cot
    0.07
     Alloy
    0.07
    SSC
    0.07
     overtime
    0.07
     �
    0.07
    Activations Density 0.001%

    No Known Activations