© 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. 5831
    Prev
    Next
    INDEX
    Explanations

    say "ize"

    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
    صالات
    -0.09
     deeg
    -0.09
    durch
    -0.09
     δεύτε
    -0.09
    multip
    -0.09
    invalid
    -0.08
     падтрым
    -0.08
    دىن
    -0.08
    las
    -0.08
     əlav
    -0.08
    POSITIVE LOGITS
    ize
    0.22
    izing
    0.18
    IZE
    0.16
    izes
    0.15
    ized
    0.14
    ise
    0.14
    izer
    0.12
    IZED
    0.11
    ises
    0.11
    izei
    0.10
    Activations Density 0.005%

    No Known Activations