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. 9028
    Prev
    Next
    INDEX
    Explanations

    aroma

    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
    ชาย
    -0.08
     Rand
    -0.08
     Nations
    -0.07
     havia
    -0.07
    iron
    -0.07
    יו
    -0.07
    �
    -0.07
    GUILayout
    -0.07
     habría
    -0.07
    Iron
    -0.07
    POSITIVE LOGITS
     agradável
    0.08
     pip
    0.07
     agradable
    0.07
    /color
    0.07
     destruct
    0.07
     ụtọ
    0.07
     agréable
    0.07
    -producing
    0.07
     spores
    0.07
    /history
    0.07
    Activations Density 0.018%

    No Known Activations