© 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. 77949
    Prev
    Next
    INDEX
    Explanations

    business, us, query

    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
     frein
    -0.08
     flair
    -0.07
     Flair
    -0.07
    dor
    -0.07
    _EXCEPTION
    -0.07
    beb
    -0.07
    entino
    -0.07
    ゼ
    -0.07
    INK
    -0.07
     fels
    -0.07
    POSITIVE LOGITS
    Workers
    0.08
     discovering
    0.08
     alty
    0.08
    Pot
    0.08
     мақ
    0.08
     工
    0.07
    Bands
    0.07
     客
    0.07
    TRACT
    0.07
    MUX
    0.07
    Activations Density 0.001%

    No Known Activations