© 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. 65600
    Prev
    Next
    INDEX
    Explanations

    pivot tables

    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
     lamps
    -0.07
    rao
    -0.07
    ograph
    -0.07
     Illuminate
    -0.07
     LED
    -0.07
     Lets
    -0.07
     Election
    -0.07
     Starg
    -0.07
     Lamps
    -0.07
    -0.07
    POSITIVE LOGITS
     flattened
    0.09
    trained
    0.09
     trill
    0.08
    pren
    0.08
     flatten
    0.08
    care
    0.08
    مه
    0.08
    _flat
    0.07
     Helsinki
    0.07
    perhaps
    0.07
    Activations Density 0.000%
    No Known Activations