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. 102816
    Prev
    Next
    INDEX
    Explanations

    (row

    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
    prefs
    -0.08
    tickets
    -0.08
     прий
    -0.08
    bots
    -0.08
     vegas
    -0.08
    flight
    -0.07
     заказа
    -0.07
    singleton
    -0.07
     момента
    -0.07
     velika
    -0.07
    POSITIVE LOGITS
     সর
    0.07
    策
    0.07
    ixe
    0.07
    旁
    0.07
    	actual
    0.07
     Gry
    0.07
     kn
    0.07
    .pan
    0.07
     Rana
    0.07
     SMA
    0.07
    Activations Density 0.003%

    No Known Activations