© 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. 24706
    Prev
    Next
    INDEX
    Explanations

    magnetic fields

    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
     embal
    -0.09
     रिलीज
    -0.08
     domination
    -0.08
     renovation
    -0.08
     dominance
    -0.08
     superiority
    -0.08
     church
    -0.08
     ales
    -0.08
     Renov
    -0.08
     cottages
    -0.08
    POSITIVE LOGITS
     perpendicular
    0.14
     Yee
    0.10
     transverse
    0.10
     sideways
    0.10
     تعرض
    0.09
     ions
    0.09
    _plane
    0.09
    _geometry
    0.09
     орналас
    0.09
    紫
    0.09
    Activations Density 0.004%

    No Known Activations