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. 55882
    Prev
    Next
    INDEX
    Explanations

    ]

    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
     zunächst
    -0.07
    VERIFY
    -0.07
     ony
    -0.07
    ighbor
    -0.07
    -0.07
    	Assert
    -0.07
     सत्य
    -0.07
     устройство
    -0.07
     sayesinde
    -0.07
     অভিয
    -0.07
    POSITIVE LOGITS
     commas
    0.10
    pipes
    0.09
     Presidents
    0.08
    pel
    0.08
     finalists
    0.08
    TS
    0.08
    -separated
    0.08
     ډول
    0.08
     separating
    0.08
     PDT
    0.08
    Activations Density 0.001%

    No Known Activations