© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 47776
    Prev
    Next
    INDEX
    Explanations

    的

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eventos
    -0.09
     događ
    -0.09
     événements
    -0.09
     evento
    -0.08
     tapaht
    -0.08
     tex
    -0.08
     Nga
    -0.08
     événement
    -0.08
    Eventos
    -0.08
    Events
    -0.07
    POSITIVE LOGITS
    面
    0.12
    剂
    0.12
    大利
    0.10
     面
    0.09
    �
    0.09
    面的
    0.09
    aydi
    0.08
    lide
    0.08
     dosage
    0.08
    بل
    0.08
    Activations Density 0.001%

    No Known Activations