© 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. 2519
    Prev
    Next
    INDEX
    Explanations

    period

    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
    IDS
    -0.08
     DUI
    -0.08
     Wik
    -0.08
     Fing
    -0.08
     XK
    -0.08
     hemm
    -0.07
     väldigt
    -0.07
     zomb
    -0.07
     hem
    -0.07
     vex
    -0.07
    POSITIVE LOGITS
    。这
    0.08
     убед
    0.08
    。然而
    0.08
    。この
    0.08
     Nvidia
    0.08
    pe
    0.07
    HL
    0.07
    。不
    0.07
     narrated
    0.07
     eyes
    0.07
    Activations Density 0.048%

    No Known Activations