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. 54209
    Prev
    Next
    INDEX
    Explanations

    UI elements

    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
     धर
    -0.09
     hazardous
    -0.08
    নৈতিক
    -0.08
     тіл
    -0.08
    نامه
    -0.08
     "-"↵
    -0.07
     chaleure
    -0.07
    ူး
    -0.07
     kroner
    -0.07
    ouns
    -0.07
    POSITIVE LOGITS
    mall
    0.09
     IBOutlet
    0.09
     instantiated
    0.09
     Instantiate
    0.09
    configured
    0.08
     mounted
    0.08
     uncontrolled
    0.08
     datasource
    0.08
    controlled
    0.08
    _data
    0.08
    Activations Density 0.013%

    No Known Activations