© 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. 11-RESID-POST-AA
    6. 24862
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
     battery
    -0.09
    angé
    -0.08
     ETS
    -0.08
    _resp
    -0.08
     sizzling
    -0.07
     format
    -0.07
     boasting
    -0.07
    Battery
    -0.07
     electr
    -0.07
    _TYPED
    -0.07
    POSITIVE LOGITS
     dolayı
    0.08
    алым
    0.08
    اهی
    0.08
     dout
    0.08
    হার
    0.07
     Everybody
    0.07
    imerkiksi
    0.07
     doy
    0.07
    [a
    0.07
    েন
    0.07
    Activations Density 0.005%

    No Known Activations