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. 29793
    Prev
    Next
    INDEX
    Explanations

    RAID

    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
     offense
    -0.08
    Ed
    -0.08
     puesta
    -0.07
     cât
    -0.07
     Identify
    -0.07
    cn
    -0.07
    îne
    -0.07
    ipple
    -0.07
     Load
    -0.07
    =view
    -0.07
    POSITIVE LOGITS
     جائز
    0.09
     Sod
    0.08
    Descricao
    0.08
     تت
    0.08
    鳥
    0.08
     للف
    0.07
     массива
    0.07
     arrangement
    0.07
    Neu
    0.07
     библи
    0.07
    Activations Density 0.001%

    No Known Activations