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. 76423
    Prev
    Next
    INDEX
    Explanations

    storytelling

    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
     tardes
    -0.09
     investigating
    -0.08
     Incoming
    -0.08
     researching
    -0.08
    �
    -0.08
    Ÿ
    -0.08
     cpp
    -0.07
     nastav
    -0.07
     эксплуата
    -0.07
    াপ্ত
    -0.07
    POSITIVE LOGITS
     memorable
    0.10
     relatable
    0.09
     기억
    0.08
     anecdotes
    0.08
     persuasion
    0.08
    Remember
    0.08
     agendas
    0.08
     السلطة
    0.08
     empathy
    0.07
    Abstract
    0.07
    Activations Density 0.012%

    No Known Activations