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. 12131
    Prev
    Next
    INDEX
    Explanations

    if

    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
     engineer
    -0.08
    ingss
    -0.08
     manejo
    -0.07
    sl
    -0.07
    威
    -0.07
    thel
    -0.07
     Vivo
    -0.07
     "()
    -0.07
     ie
    -0.07
    Ст
    -0.07
    POSITIVE LOGITS
     ಹೇಳ
    0.10
     blei
    0.08
    _like
    0.08
     бас
    0.07
     образом
    0.07
    araan
    0.07
     неож
    0.07
     crimin
    0.07
    �
    0.07
    ਿਆ
    0.07
    Activations Density 0.005%

    No Known Activations