© 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. 3-RESID-POST-AA
    11. 12798
    Prev
    Next
    INDEX
    Explanations

    procedure

    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
     उद
    -0.09
     উদ
    -0.08
    Gallery
    -0.07
     وتأ
    -0.07
    gallery
    -0.07
    MIN
    -0.07
    dashboard
    -0.07
    �
    -0.07
     Saddle
    -0.07
     UCLA
    -0.07
    POSITIVE LOGITS
     Stevenson
    0.08
     Chan
    0.08
    skosten
    0.08
    итай
    0.08
     Scott
    0.08
     ddim
    0.07
    વિ
    0.07
     blindly
    0.07
     chauffeur
    0.07
     paramount
    0.07
    Activations Density 0.004%

    No Known Activations