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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 88218
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    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
    Jesu
    -0.08
    pecific
    -0.08
     välj
    -0.08
     जम्म
    -0.08
     tve
    -0.08
    igital
    -0.08
     अतिरिक्त
    -0.08
     escalating
    -0.08
     који
    -0.08
     whim
    -0.08
    POSITIVE LOGITS
     થય
    0.08
    中央値
    0.08
    ading
    0.07
    .mean
    0.07
    ouw
    0.07
    平均との差
    0.07
    Derived
    0.07
    /home
    0.07
    quart
    0.07
     সহ
    0.07
    Activations Density 0.022%

    No Known Activations