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. 43434
    Prev
    Next
    INDEX
    Explanations

    mee

    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
     toga
    -0.09
     spotting
    -0.09
    .separator
    -0.08
     Orn
    -0.08
     Bd
    -0.08
    .inspect
    -0.08
     gerade
    -0.08
     deta
    -0.08
     minded
    -0.08
     mort
    -0.08
    POSITIVE LOGITS
     fidèle
    0.08
     Kindle
    0.08
    ילות
    0.08
    Downloading
    0.08
    现金
    0.08
    faith
    0.08
    -story
    0.08
     Kodi
    0.08
    factor
    0.07
    _download
    0.07
    Activations Density 0.069%

    No Known Activations