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. 120189
    Prev
    Next
    INDEX
    Explanations

    sam

    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
    orneo
    -0.08
    atoj
    -0.08
     aix
    -0.07
    یر
    -0.07
     چ
    -0.07
     reparto
    -0.07
     Residents
    -0.07
     artisans
    -0.07
     NSW
    -0.07
     Tour
    -0.07
    POSITIVE LOGITS
     lekk
    0.09
     drank
    0.08
     dad
    0.08
     brind
    0.08
     pappa
    0.08
    )application
    0.08
     bebida
    0.07
     father
    0.07
     pijn
    0.07
     pipeline
    0.07
    Activations Density 0.001%

    No Known Activations