© 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. 11-RESID-POST-AA
    11. 29610
    Prev
    Next
    INDEX
    Explanations

    Parenthesis and "or"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     多
    -0.08
     expanding
    -0.07
     വ്യാപ
    -0.07
    elend
    -0.07
     判断
    -0.07
     complexities
    -0.07
     tăng
    -0.07
     distr
    -0.07
     expansion
    -0.07
     NB
    -0.07
    POSITIVE LOGITS
    -medium
    0.09
     제외
    0.09
     medios
    0.08
    mods
    0.08
     будуць
    0.08
    注明
    0.08
    ahead
    0.08
    _medium
    0.08
    MOD
    0.08
    itati
    0.07
    Activations Density 0.007%

    No Known Activations