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. 112271
    Prev
    Next
    INDEX
    Explanations

    First come first served

    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
     softly
    -0.08
     getan
    -0.08
    柔
    -0.07
     мяг
    -0.07
    ightly
    -0.07
     જીવન
    -0.07
    เม
    -0.07
    tage
    -0.07
     lifecycle
    -0.07
     grade
    -0.07
    POSITIVE LOGITS
     Monument
    0.09
     monuments
    0.08
    付款
    0.08
     যারা
    0.08
     monument
    0.08
    .reserve
    0.08
     भुगतान
    0.08
     malheureusement
    0.08
     Payments
    0.08
     monetize
    0.08
    Activations Density 0.005%

    No Known Activations