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. 112181
    Prev
    Next
    INDEX
    Explanations

    explain

    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
    -era
    -0.08
     উদ্ব
    -0.08
     Jews
    -0.08
     erwäh
    -0.08
     maniera
    -0.08
    иялық
    -0.08
    了一等奖
    -0.08
    iança
    -0.08
     fires
    -0.08
     tempi
    -0.08
    POSITIVE LOGITS
     imposs
    0.08
     почему
    0.08
     hvorfor
    0.08
     irre
    0.07
     waarom
    0.07
     satisfied
    0.07
     violated
    0.07
    bab
    0.07
    rets
    0.07
    adilla
    0.07
    Activations Density 0.005%

    No Known Activations