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. 61062
    Prev
    Next
    INDEX
    Explanations

    for

    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
     धीरे
    -0.08
    ీజ్
    -0.08
     مقاومت
    -0.08
     Inspire
    -0.08
     inspiring
    -0.08
    øse
    -0.08
     inspire
    -0.08
    biotic
    -0.08
     abolition
    -0.07
    ße
    -0.07
    POSITIVE LOGITS
     happened
    0.08
    武汉
    0.07
     tungsten
    0.07
    .Bad
    0.07
    .Stretch
    0.07
     Wang
    0.07
    ОМ
    0.07
    ianas
    0.07
     arrived
    0.07
    Tik
    0.06
    Activations Density 0.002%

    No Known Activations