© 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. 96946
    Prev
    Next
    INDEX
    Explanations

    say "rate"

    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
     maxima
    -0.09
    пер
    -0.08
    బ్బ
    -0.08
     það
    -0.08
    kiä
    -0.08
     ilm
    -0.08
     ehkä
    -0.08
     comuns
    -0.08
     dál
    -0.08
     chete
    -0.08
    POSITIVE LOGITS
    rate
    0.14
    rese
    0.09
    -rate
    0.09
    strate
    0.09
    (rate
    0.08
    yele
    0.08
    jal
    0.08
    _RATE
    0.08
    lc
    0.08
    RATE
    0.08
    Activations Density 0.000%

    No Known Activations