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. 109970
    Prev
    Next
    INDEX
    Explanations

    B-roll video footage

    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
    ziplin
    -0.08
     medicijnen
    -0.08
     withholding
    -0.07
    disc
    -0.07
     medicamentos
    -0.07
    ISC
    -0.07
    의를
    -0.07
    ’O
    -0.07
    座
    -0.07
     Einrichtung
    -0.07
    POSITIVE LOGITS
     footage
    0.15
    摄
    0.08
    0.08
     पुर
    0.08
     serai
    0.08
     bridal
    0.07
     cotton
    0.07
     velvet
    0.07
     helicopter
    0.07
     provenant
    0.07
    Activations Density 0.013%

    No Known Activations