© 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. 102920
    Prev
    Next
    INDEX
    Explanations

    miracle

    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
     penalties
    -0.08
     luyện
    -0.08
    щие
    -0.08
    zc
    -0.07
     abusive
    -0.07
     aggressive
    -0.07
    ished
    -0.07
    stered
    -0.07
     agres
    -0.07
     and
    -0.07
    POSITIVE LOGITS
     miraculous
    0.16
     miracles
    0.15
     milag
    0.14
     miracle
    0.14
     marvelous
    0.14
    τουργ
    0.13
     чуд
    0.13
     wond
    0.13
     wonders
    0.12
    妙
    0.12
    Activations Density 0.011%

    No Known Activations