© 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. 78387
    Prev
    Next
    INDEX
    Explanations

    must

    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
     Slight
    -0.09
    kbd
    -0.08
     betrekking
    -0.08
     légèrement
    -0.08
     histogram
    -0.08
    ellus
    -0.07
    _callable
    -0.07
     Ked
    -0.07
     inspiratie
    -0.07
    针对
    -0.07
    POSITIVE LOGITS
     guardians
    0.10
     ensuing
    0.10
     jeopard
    0.09
     Trag
    0.09
    বেন
    0.09
     risking
    0.09
     escalating
    0.09
    揭
    0.09
     supernatural
    0.08
     promete
    0.08
    Activations Density 0.147%

    No Known Activations