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. 65088
    Prev
    Next
    INDEX
    Explanations

    <title

    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
    otherap
    -0.09
     upbringing
    -0.08
    -produced
    -0.08
    anzi
    -0.08
     kodi
    -0.08
     existe
    -0.07
     fraction
    -0.07
    oux
    -0.07
     Bath
    -0.07
     observ
    -0.07
    POSITIVE LOGITS
    Title
    0.10
     title
    0.09
    <title
    0.09
     제목
    0.08
    Portfolio
    0.08
     Transitional
    0.08
    (title
    0.08
     Titel
    0.08
    _TITLE
    0.08
    Titel
    0.08
    Activations Density 0.002%

    No Known Activations