Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 78477
    Prev
    Next
    INDEX
    Explanations

    Riemann sums

    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
     retrouve
    -0.09
     карта
    -0.09
     diseng
    -0.08
     лиш
    -0.08
     вода
    -0.07
     themed
    -0.07
     gig
    -0.07
     vea
    -0.07
    hingga
    -0.07
     повтор
    -0.07
    POSITIVE LOGITS
     centroid
    0.13
    中央値
    0.11
     midpoint
    0.11
    :center
    0.10
     કેન્દ્ર
    0.10
    中央
    0.10
     중앙
    0.10
     averages
    0.10
     కేంద్ర
    0.10
     representative
    0.10
    Activations Density 0.027%

    No Known Activations