© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5570
    Prev
    Next
    INDEX
    Explanations

    サ

    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
    =L
    -0.08
    包括
    -0.07
     snowfall
    -0.07
    steil
    -0.07
     کا
    -0.07
    Tree
    -0.07
    -0.07
    araoh
    -0.07
    ossz
    -0.07
     kee
    -0.07
    POSITIVE LOGITS
    ポ
    0.12
    ンプ
    0.12
    ーバ
    0.11
    イド
    0.10
    マー
    0.09
    cers
    0.08
    		                   
    0.08
    ービ
    0.08
    イク
    0.08
    łat
    0.08
    Activations Density 0.000%
    No Known Activations