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. 60988
    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
     Sock
    -0.08
     Cookies
    -0.08
     하지만
    -0.08
     Experiences
    -0.08
     Recently
    -0.08
    Recently
    -0.08
     lass
    -0.07
     ఇటీవల
    -0.07
     experiences
    -0.07
     lately
    -0.07
    POSITIVE LOGITS
    'ici
    0.09
     hopefully
    0.09
     सके
    0.09
     सक
    0.08
    validated
    0.08
    ✅
    0.08
    ме
    0.08
     siap
    0.08
    ✔
    0.08
     executable
    0.08
    Activations Density 0.024%

    No Known Activations