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. 52927
    Prev
    Next
    INDEX
    Explanations

    page

    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
     لا
    -0.08
     kaya
    -0.07
     место
    -0.07
     Kai
    -0.07
    देख
    -0.07
     shiny
    -0.07
     Kama
    -0.07
    gone
    -0.07
     mating
    -0.07
     Kör
    -0.07
    POSITIVE LOGITS
     agar
    0.08
     osob
    0.08
    幅
    0.08
     lease
    0.08
     dioxide
    0.07
    quist
    0.07
    holders
    0.07
     individ
    0.07
     horiz
    0.07
    grav
    0.07
    Activations Density 0.019%

    No Known Activations