© 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. 7-RESID-POST-AA
    11. 1195
    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_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flyer
    -0.08
     flyer
    -0.08
    hair
    -0.08
     выпуска
    -0.08
    -0.07
     fingerprints
    -0.07
     Flying
    -0.07
     Hair
    -0.07
     Pilot
    -0.07
     feder
    -0.07
    POSITIVE LOGITS
     carv
    0.08
    最长
    0.08
     ere
    0.08
     efectu
    0.08
    。如果
    0.08
    qry
    0.08
    (mid
    0.08
    。因此
    0.08
    .discord
    0.08
    ，就是
    0.08
    Activations Density 0.176%

    No Known Activations