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

    Neuronpedia

    APICircuit 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. 15-RESID-POST-AA
    6. 68
    Prev
    Next
    INDEX
    Explanations

    inside

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     interactions
    -0.07
     NEGLIGENCE
    -0.07
     counterparts
    -0.07
     sogenannten
    -0.07
     The
    -0.07
    -0.07
    oppel
    -0.07
     φορές
    -0.07
     most
    -0.07
     APIs
    -0.07
    POSITIVE LOGITS
     reachable
    0.10
    范围
    0.10
     plage
    0.10
     laarin
    0.09
     jurisd
    0.09
    Accessible
    0.09
    reachable
    0.09
    кті
    0.09
     ضمن
    0.09
    Included
    0.09
    Activations Density 0.012%

    No Known Activations