Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 90225
    Prev
    Next
    INDEX
    Explanations

    draw

    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
     gut
    -0.08
    Gut
    -0.08
    -0.08
    Xu
    -0.08
    god
    -0.08
     xã
    -0.07
    IRO
    -0.07
     Gut
    -0.07
    nement
    -0.07
     intimate
    -0.07
    POSITIVE LOGITS
     Freder
    0.08
    出的
    0.08
     lump
    0.08
     Richard
    0.08
     Starr
    0.07
     wad
    0.07
    smanship
    0.07
     ata
    0.07
     Bip
    0.07
     Carm
    0.07
    Activations Density 0.022%

    No Known Activations