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. 87990
    Prev
    Next
    INDEX
    Explanations

    greek life

    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
     ascent
    -0.08
     nasa
    -0.08
     Galileo
    -0.08
     GX
    -0.08
     '"'
    -0.08
     author's
    -0.07
    Dialect
    -0.07
    GX
    -0.07
    Whitespace
    -0.07
     waarmee
    -0.07
    POSITIVE LOGITS
     festas
    0.10
     backpack
    0.10
     sophomore
    0.10
     freshmen
    0.10
     rites
    0.10
    fashion
    0.09
     rituals
    0.09
     freshman
    0.09
     Fashion
    0.09
     коллед
    0.09
    Activations Density 0.055%

    No Known Activations