© 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. 95383
    Prev
    Next
    INDEX
    Explanations

    word searches

    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
     Divorce
    -0.08
    identity
    -0.08
    broker
    -0.08
    Insight
    -0.08
    cheduler
    -0.08
    .ico
    -0.08
    284
    -0.08
    _${
    -0.08
     overhaul
    -0.07
    282
    -0.07
    POSITIVE LOGITS
     horizontally
    0.11
     directions
    0.11
     directional
    0.11
     Directions
    0.10
     horizontal
    0.10
     diagon
    0.10
     direction
    0.09
     vertically
    0.09
     horizont
    0.09
     दिश
    0.09
    Activations Density 0.010%

    No Known Activations