© 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. 3-RESID-POST-AA
    11. 13096
    Prev
    Next
    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bearing
    -0.08
    -0.07
    拟
    -0.07
    运营
    -0.07
     tra
    -0.07
     ayud
    -0.07
    先生
    -0.07
     invariant
    -0.07
     लाग
    -0.07
     chứa
    -0.07
    POSITIVE LOGITS
     Bab
    0.10
     labyrinth
    0.09
    Bab
    0.08
     gare
    0.08
    Gloss
    0.08
    �
    0.08
     retval
    0.07
    Verifier
    0.07
     Stanford
    0.07
    Retro
    0.07
    Activations Density 0.002%
    No Known Activations