© 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. 11-RESID-POST-AA
    11. 95069
    Prev
    Next
    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Moz
    -0.08
     Einsatz
    -0.08
     Mose
    -0.07
    大会
    -0.07
     �
    -0.07
    EV
    -0.07
     Nairobi
    -0.07
    杭
    -0.07
     OSHA
    -0.07
    之外
    -0.07
    POSITIVE LOGITS
     faithful
    0.08
     kasar
    0.08
    -rich
    0.08
    下さい
    0.07
    For
    0.07
     degraded
    0.07
     Mediterr
    0.07
    ਤੇ
    0.07
    ahal
    0.07
    ください
    0.07
    Activations Density 0.007%

    No Known Activations