© 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. 97413
    Prev
    Next
    INDEX
    Explanations

    Two letters ending in S

    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
    840
    -0.09
     �
    -0.09
    龙江
    -0.09
     龙头
    -0.08
    怡
    -0.08
    .•
    -0.08
    �
    -0.08
     Punjabi
    -0.08
     Xiao
    -0.08
     ■
    -0.08
    POSITIVE LOGITS
     DS
    0.40
     HS
    0.39
     RS
    0.38
     BS
    0.36
     GS
    0.36
     LS
    0.35
     QS
    0.35
     WS
    0.35
     FS
    0.34
     TS
    0.34
    Activations Density 0.638%

    No Known Activations