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. 98315
    Prev
    Next
    INDEX
    Explanations

    say "s" word

    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
     razões
    -0.08
    Ậ
    -0.08
     domingos
    -0.08
     ימ
    -0.07
    /DC
    -0.07
     Right
    -0.07
     razones
    -0.07
    დილ
    -0.07
     raisons
    -0.07
     rares
    -0.07
    POSITIVE LOGITS
    (rr
    0.16
     rr
    0.16
    (RE
    0.15
     రె
    0.15
     റെ
    0.14
     RD
    0.13
    (rd
    0.13
     RE
    0.13
     rl
    0.13
     RL
    0.13
    Activations Density 0.101%

    No Known Activations