© 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. 26430
    Prev
    Next
    INDEX
    Explanations

    's

    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
    unis
    -0.08
     exig
    -0.08
     Decreto
    -0.08
    NL
    -0.07
    urd
    -0.07
     AMA
    -0.07
     Seychelles
    -0.07
    (DE
    -0.07
     modify
    -0.07
     requirement
    -0.07
    POSITIVE LOGITS
     gaining
    0.09
     rising
    0.09
     ವಿಜಯ
    0.08
     Rising
    0.08
    佩
    0.08
     awakening
    0.08
     wächst
    0.08
     задум
    0.08
     uphill
    0.08
     fiú
    0.08
    Activations Density 0.006%

    No Known Activations