© 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. 778
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     Hopefully
    -0.08
     �
    -0.08
     Soto
    -0.07
    _rsp
    -0.07
     sujeito
    -0.07
     childhood
    -0.07
    零
    -0.07
    mete
    -0.07
     Sne
    -0.07
     delic
    -0.07
    POSITIVE LOGITS
     ACT
    0.08
     AN
    0.08
    ipos
    0.07
    TH
    0.07
    CH
    0.07
    ERVER
    0.07
     HE
    0.07
     Holding
    0.07
     wat
    0.07
    ICIAL
    0.07
    Activations Density 0.279%

    No Known Activations