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. 98188
    Prev
    Next
    INDEX
    Explanations

    say "rabbit"

    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
     Φ
    -0.11
     Kurd
    -0.11
     PSD
    -0.11
     ZE
    -0.11
     HD
    -0.11
     PD
    -0.10
     晋
    -0.10
     TD
    -0.10
     OD
    -0.10
     aço
    -0.10
    POSITIVE LOGITS
     rabbit
    0.56
     Rabbit
    0.55
    Rabbit
    0.54
     rabbits
    0.53
    兔
    0.53
    rabbit
    0.51
    .rabbit
    0.48
     bunny
    0.43
     Rabb
    0.40
     Bunny
    0.35
    Activations Density 0.047%

    No Known Activations