© 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. 11-RESID-POST-AA
    11. 44492
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    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
    。”↵↵
    -0.09
     ফির
    -0.08
     pastor
    -0.08
     uiteindelijk
    -0.08
    。所以
    -0.08
    甚至
    -0.08
    ্রি
    -0.08
    —you
    -0.08
     pastors
    -0.08
     ultimately
    -0.07
    POSITIVE LOGITS
    검
    0.08
    ווען
    0.07
    כנ
    0.07
     검
    0.07
     naman
    0.07
    වැ
    0.07
    perm
    0.07
    pare
    0.07
     Tahoe
    0.07
     pare
    0.07
    Activations Density 0.545%

    No Known Activations