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

    Neuronpedia

    Jacobian LensNEW
    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. 69368
    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
    oune
    -0.09
     bulundu
    -0.08
    uggestions
    -0.08
    -0.08
     일반
    -0.08
     ڪ
    -0.08
    突出
    -0.07
     kaf
    -0.07
    quotation
    -0.07
    rechter
    -0.07
    POSITIVE LOGITS
     Additionally
    0.10
    Additionally
    0.09
    与此同时
    0.09
     Meanwhile
    0.08
     additionally
    0.08
     daarnaast
    0.08
     simultaneously
    0.08
     samtidig
    0.08
     Daarnaast
    0.08
     secondly
    0.08
    Activations Density 0.194%
    No Known Activations