© 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. 23-RESID-POST-AA
    11. 5466
    Prev
    Next
    INDEX
    Explanations

    小

    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
     Grünen
    -0.08
    finder
    -0.07
    莎
    -0.07
     captions
    -0.07
     gawa
    -0.07
     گرم
    -0.07
    green
    -0.07
     Organic
    -0.07
    ntag
    -0.07
     проб
    -0.07
    POSITIVE LOGITS
     privilege
    0.18
    Privilege
    0.16
    priv
    0.16
     privil
    0.16
     Priv
    0.15
     privileges
    0.15
    权限
    0.14
     privilégi
    0.14
     privileged
    0.14
     privile
    0.14
    Activations Density 0.003%

    No Known Activations