© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 29659
    Prev
    Next
    INDEX
    Explanations

    Explanations in a discussion

    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
     paragraphs
    -0.09
     paragraph
    -0.08
     );↵↵
    -0.08
    );↵↵
    -0.08
     nhớ
    -0.08
     unsure
    -0.08
    Paragraph
    -0.08
    "];↵↵
    -0.08
    ührung
    -0.08
    Candidates
    -0.08
    POSITIVE LOGITS
     Why
    0.12
     why
    0.12
    why
    0.12
     waarom
    0.11
     varför
    0.11
    Why
    0.10
     Почему
    0.10
    为什么
    0.10
     Warum
    0.10
     কেন
    0.10
    Activations Density 0.063%

    No Known Activations