© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 96746
    Prev
    Next
    INDEX
    Explanations

    say "ye or ir"

    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
     Lied
    -0.08
    iseren
    -0.08
    ំ
    -0.08
    Vect
    -0.08
    ają
    -0.08
     destinado
    -0.08
    (dest
    -0.08
    ingss
    -0.08
    _dest
    -0.08
    ITI
    -0.08
    POSITIVE LOGITS
    ye
    0.17
    ya
    0.15
    yo
    0.14
    yan
    0.13
    yele
    0.12
    yez
    0.11
    yes
    0.11
    y
    0.10
    YO
    0.10
    yu
    0.10
    Activations Density 0.001%

    No Known Activations