© 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. 3-RESID-POST-AA
    11. 2741
    Prev
    Next
    INDEX
    Explanations

    angry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     syst
    -0.08
     год
    -0.08
     Via
    -0.07
     Boc
    -0.07
     UIL
    -0.07
     Beacon
    -0.07
     الغذ
    -0.07
     Jake
    -0.07
     MIG
    -0.07
     MAS
    -0.07
    POSITIVE LOGITS
    	ft
    0.08
     Harr
    0.07
     घे
    0.07
    腾
    0.07
    曲
    0.07
    പ്പം
    0.07
    迫
    0.07
    充分
    0.07
     Krak
    0.07
    appa
    0.07
    Activations Density 0.003%

    No Known Activations