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. 43255
    Prev
    Next
    INDEX
    Explanations

    Thermopylae Battle

    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
     ICT
    -0.08
     anex
    -0.08
     sanc
    -0.08
     оператив
    -0.08
     reconhecimento
    -0.07
     Dop
    -0.07
     see
    -0.07
     dop
    -0.07
     Fourier
    -0.07
     poderes
    -0.07
    POSITIVE LOGITS
    gol
    0.08
     famously
    0.08
     cervical
    0.08
    िकी
    0.08
    	my
    0.07
     Stainless
    0.07
     halimbawa
    0.07
     portion
    0.07
     contacted
    0.07
    	static
    0.07
    Activations Density 0.005%

    No Known Activations