© 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. 19-RESID-POST-AA
    11. 102721
    Prev
    Next
    INDEX
    Explanations

    ]

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    两个
    -0.08
     ersten
    -0.08
    etric
    -0.08
    first
    -0.08
    .original
    -0.08
    .first
    -0.08
    (orig
    -0.08
    不上
    -0.08
     basics
    -0.07
    .orig
    -0.07
    POSITIVE LOGITS
     ಮತ್ತೆ
    0.20
     tekrar
    0.19
     ફરી
    0.19
     again
    0.18
     വീണ്ടും
    0.18
     আবার
    0.18
     reiter
    0.17
     AGAIN
    0.17
     снова
    0.17
     שוב
    0.16
    Activations Density 0.002%

    No Known Activations