© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 16447
    Prev
    Next
    INDEX
    Explanations

    uniqueness

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wget
    -0.09
    คะแนน
    -0.09
     leaderboard
    -0.08
     whitelist
    -0.08
    今回
    -0.08
    -uppercase
    -0.08
    สาร
    -0.08
     checkpoint
    -0.08
     malware
    -0.08
     mafia
    -0.08
    POSITIVE LOGITS
     uniqueness
    0.12
     coax
    0.10
     существует
    0.09
     uniquely
    0.09
     meerdere
    0.09
     infinitely
    0.09
     Finden
    0.09
    无限
    0.09
     множество
    0.09
     шара
    0.09
    Activations Density 0.016%

    No Known Activations