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. 23-RESID-POST-AA
    6. 98539
    Prev
    Next
    INDEX
    Explanations

    Thoughtful writing

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ...
    -0.14
     Also
    -0.13
     "
    -0.13
     also
    -0.13
     “
    -0.12
     ?
    -0.12
     ???
    -0.12
    ...?
    -0.12
     &#
    -0.12
     =
    -0.12
    POSITIVE LOGITS
     thoughtful
    0.16
     thoughtfully
    0.16
     diligent
    0.15
     diligently
    0.15
     wisely
    0.14
     vigilant
    0.14
     savvy
    0.13
     heartfelt
    0.13
     meticulous
    0.13
     steadfast
    0.13
    Activations Density 0.136%

    No Known Activations