© 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. 97379
    Prev
    Next
    INDEX
    Explanations

    say "ب" words

    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
    jm
    -0.09
    WIN
    -0.08
    aju
    -0.08
    Borrow
    -0.08
    qt
    -0.08
    q
    -0.08
    Lag
    -0.08
    qm
    -0.07
     Adopt
    -0.07
    vj
    -0.07
    POSITIVE LOGITS
    بد
    0.12
    بعاد
    0.11
    بعد
    0.11
     big
    0.09
    -big
    0.08
     가능합니다
    0.08
     Ihrer
    0.08
     대신
    0.08
    שלום
    0.07
    (big
    0.07
    Activations Density 0.001%

    No Known Activations