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. 98929
    Prev
    Next
    INDEX
    Explanations

    $,

    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
    ेली
    -0.07
     precipit
    -0.07
    atriz
    -0.07
    (em
    -0.07
    排序
    -0.07
    irectory
    -0.07
    (res
    -0.07
    ışı
    -0.07
     bem
    -0.07
     imam
    -0.07
    POSITIVE LOGITS
     course
    0.08
     tariff
    0.08
    cookie
    0.08
     cookie
    0.08
    cron
    0.08
     wallpaper
    0.08
     كور
    0.07
     бүл
    0.07
     rama
    0.07
     приобр
    0.07
    Activations Density 0.006%

    No Known Activations