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. 113951
    Prev
    Next
    INDEX
    Explanations

    the

    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
    糕
    -0.09
     pity
    -0.08
    pane
    -0.08
     asfalt
    -0.08
     Paulista
    -0.08
     municipality
    -0.08
    .restaurant
    -0.07
    .Router
    -0.07
    /dist
    -0.07
    /plain
    -0.07
    POSITIVE LOGITS
    -eme
    0.09
     cybersecurity
    0.08
    _quote
    0.08
    -Aug
    0.08
     augmenté
    0.08
     cybers
    0.08
     цаг
    0.08
     დრ
    0.08
    -akw
    0.08
     firearms
    0.08
    Activations Density 0.044%

    No Known Activations