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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 64367
    Prev
    Next
    INDEX
    Explanations

    Millions

    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
     tactile
    -0.09
    �
    -0.08
     metallic
    -0.08
    剤
    -0.08
     discomfort
    -0.08
    лас
    -0.08
     stiffness
    -0.08
     Wichtig
    -0.07
    nerg
    -0.07
    ̆
    -0.07
    POSITIVE LOGITS
     millions
    0.14
     readership
    0.12
     लाख
    0.11
     million
    0.11
     milions
    0.11
     milioni
    0.10
    点赞
    0.10
     Millions
    0.10
     millones
    0.10
     lượt
    0.10
    Activations Density 0.033%

    No Known Activations