© 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. 19-RESID-POST-AA
    11. 102675
    Prev
    Next
    INDEX
    Explanations

    体

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olate
    -0.08
     mungkin
    -0.07
    alwa
    -0.07
    年来
    -0.07
    PP
    -0.07
     olm
    -0.07
     protecting
    -0.07
    ל
    -0.07
    ord
    -0.07
    อลล
    -0.07
    POSITIVE LOGITS
    悟
    0.11
    otify
    0.10
    험
    0.09
    merkt
    0.09
    彩彩票
    0.08
     merken
    0.08
     merkt
    0.08
     erkennt
    0.08
     herkennen
    0.08
    izeit
    0.08
    Activations Density 0.001%

    No Known Activations