© 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. 48571
    Prev
    Next
    INDEX
    Explanations

    say "also"

    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
    ẹlu
    -0.08
     pitanju
    -0.07
    -первых
    -0.07
    aaring
    -0.06
    oped
    -0.06
    ieważ
    -0.06
    uniya
    -0.06
    '])[
    -0.06
    onas
    -0.06
    ))/(
    -0.06
    POSITIVE LOGITS
     also
    0.76
     também
    0.73
     también
    0.71
     также
    0.71
    also
    0.71
     også
    0.70
     également
    0.70
     також
    0.69
     també
    0.68
     också
    0.67
    Activations Density 3.356%

    No Known Activations