© 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. 108769
    Prev
    Next
    INDEX
    Explanations

    clue

    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
     pharm
    -0.08
    orum
    -0.07
    龙
    -0.07
    ums
    -0.07
    ée
    -0.07
     definitive
    -0.07
    Lil
    -0.07
    IELD
    -0.07
     Barrett
    -0.07
     Lil
    -0.07
    POSITIVE LOGITS
     واسعة
    0.09
    _locations
    0.08
     Kuna
    0.08
    �
    0.08
     왜
    0.08
     carbo
    0.07
     τι
    0.07
     fish
    0.07
    itate
    0.07
    కు
    0.07
    Activations Density 0.005%

    No Known Activations