Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 53056
    Prev
    Next
    INDEX
    Explanations

    button

    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
     visitar
    -0.08
     jungle
    -0.08
     harmony
    -0.08
     evitar
    -0.08
     Afrika
    -0.07
    วันที่
    -0.07
     kde
    -0.07
     specialty
    -0.07
     Kylie
    -0.07
     স্ত
    -0.07
    POSITIVE LOGITS
    controls
    0.10
     wiring
    0.09
     keypad
    0.08
    Interrupt
    0.08
     wired
    0.08
     pins
    0.08
     debounce
    0.08
     wires
    0.08
    	wire
    0.08
     controls
    0.08
    Activations Density 0.003%

    No Known Activations