© 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. 96959
    Prev
    Next
    INDEX
    Explanations

    someone in other languages

    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
     verdere
    -0.08
    .Cryptography
    -0.08
    .Month
    -0.08
    .Low
    -0.08
    .article
    -0.08
    .Pointer
    -0.08
    .remaining
    -0.08
    .Version
    -0.08
    .Left
    -0.08
    .Cos
    -0.08
    POSITIVE LOGITS
    别人
    0.38
     someone
    0.38
     someone's
    0.37
     alguien
    0.35
     alguém
    0.35
     quelqu
    0.35
     iemand
    0.34
     qualcuno
    0.33
     jemand
    0.33
     Someone
    0.33
    Activations Density 0.165%

    No Known Activations