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. 8709
    Prev
    Next
    INDEX
    Explanations

    202

    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
     komplik
    -0.09
     મુશ્ક
    -0.08
        ↵    ↵
    -0.08
     ослож
    -0.08
    arni
    -0.08
    	my
    -0.08
     рассматри
    -0.08
     Terrier
    -0.08
    _MY
    -0.08
     løsning
    -0.08
    POSITIVE LOGITS
    越来越
    0.09
     steadily
    0.08
    -assets
    0.08
     surpassed
    0.08
     incroy
    0.08
     Injector
    0.07
     جدید
    0.07
    ाओं
    0.07
     rapidly
    0.07
    -arrow
    0.07
    Activations Density 0.014%

    No Known Activations