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. 102969
    Prev
    Next
    INDEX
    Explanations

    hype

    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
     superiores
    -0.10
     milhares
    -0.08
     الشر
    -0.08
     malik
    -0.08
     Igre
    -0.08
    Кыргыз
    -0.08
     Dam
    -0.08
     Dug
    -0.07
     slices
    -0.07
     ев
    -0.07
    POSITIVE LOGITS
     hype
    0.17
     buzz
    0.13
     вокруг
    0.12
    buzz
    0.10
     حول
    0.09
    /de
    0.09
     поводу
    0.09
     surrounding
    0.08
     scandals
    0.08
     fuss
    0.08
    Activations Density 0.027%

    No Known Activations