© 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. 3-RESID-POST-AA
    11. 1265
    Prev
    Next
    INDEX
    Explanations

    ape

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kuat
    -0.08
    充分
    -0.08
     임
    -0.08
    (Be
    -0.08
     Beef
    -0.08
     б
    -0.08
     din
    -0.08
     sejak
    -0.08
     pleinement
    -0.07
     ಮಾನ
    -0.07
    POSITIVE LOGITS
    _hd
    0.08
     philanth
    0.08
    عر
    0.08
    .withdraw
    0.07
    cloth
    0.07
     lymph
    0.07
    QUEST
    0.07
    KO
    0.07
    Leaderboard
    0.07
     monitored
    0.07
    Activations Density 0.002%

    No Known Activations