© 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. 12932
    Prev
    Next
    INDEX
    Explanations

    是

    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
     Tae
    -0.08
     SER
    -0.08
    态
    -0.08
    柴
    -0.08
     rech
    -0.08
    群
    -0.08
     Catch
    -0.07
     Bottle
    -0.07
     Castillo
    -0.07
     basa
    -0.07
    POSITIVE LOGITS
     specialization
    0.08
    33
    0.08
    PT
    0.07
     liik
    0.07
     PT
    0.07
    _lo
    0.07
     topl
    0.07
     alleged
    0.07
     entrepreneurial
    0.07
     factual
    0.07
    Activations Density 0.004%

    No Known Activations