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. 67215
    Prev
    Next
    INDEX
    Explanations

    G

    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
     SNC
    -0.08
    (connect
    -0.08
    ledo
    -0.08
     Rox
    -0.07
     czego
    -0.07
     explain
    -0.07
     Nancy
    -0.07
     chou
    -0.07
     chất
    -0.07
    urations
    -0.07
    POSITIVE LOGITS
    很好
    0.08
     Traders
    0.08
     ya
    0.07
     UIT
    0.07
    wegen
    0.07
     tablas
    0.07
     telas
    0.07
     trgov
    0.07
    stay
    0.07
     kolon
    0.07
    Activations Density 0.002%

    No Known Activations