© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 1193
    Prev
    Next
    INDEX
    Explanations

    with

    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
     sheltered
    -0.08
    繁
    -0.08
     wale
    -0.08
    mitting
    -0.08
     parag
    -0.07
     gradual
    -0.07
    ryd
    -0.07
    .cf
    -0.07
     desfr
    -0.07
     pesticide
    -0.07
    POSITIVE LOGITS
     الحدود
    0.08
     Creativity
    0.07
     Data
    0.07
     prove
    0.07
     الهند
    0.07
     эт
    0.07
     возможность
    0.07
     National
    0.07
    _disable
    0.07
    _gold
    0.07
    Activations Density 0.020%

    No Known Activations