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. 27399
    Prev
    Next
    INDEX
    Explanations

    Cone surface area

    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
     المحلية
    -0.08
     الأولى
    -0.08
    <X
    -0.08
     сделки
    -0.07
     меш
    -0.07
     Gefühle
    -0.07
    ಲ್ಲ
    -0.07
     счет
    -0.07
    μη
    -0.07
    _Event
    -0.07
    POSITIVE LOGITS
     unnatural
    0.08
     soda
    0.08
     prostata
    0.08
     Superstar
    0.08
    ฯ
    0.08
    cession
    0.08
     commencement
    0.08
    0.08
    .Sc
    0.07
     جول
    0.07
    Activations Density 0.002%

    No Known Activations