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. 43121
    Prev
    Next
    INDEX
    Explanations

    arrow

    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
     lockdown
    -0.08
     зад
    -0.08
    igné
    -0.08
    (progress
    -0.07
    Orm
    -0.07
     Batman
    -0.07
    ("./
    -0.07
     barrage
    -0.07
    iberal
    -0.07
    Plots
    -0.07
    POSITIVE LOGITS
    待遇
    0.08
    markt
    0.08
     tangan
    0.07
     envolver
    0.07
    회의
    0.07
     பே
    0.07
     �
    0.07
     ഷ
    0.07
     tahan
    0.07
     blanc
    0.07
    Activations Density 0.001%

    No Known Activations