© 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. 3-RESID-POST-AA
    6. 895
    Prev
    Next
    INDEX
    Explanations

    math and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ves
    -0.08
     cig
    -0.08
     ibi
    -0.08
    percent
    -0.08
     fug
    -0.08
    möglichkeiten
    -0.07
     lymphoma
    -0.07
    .content
    -0.07
    thumb
    -0.07
    beheer
    -0.07
    POSITIVE LOGITS
     Astr
    0.08
     Bro
    0.08
     Menge
    0.08
     Mer
    0.07
    매
    0.07
     enclosure
    0.07
     매
    0.07
     Galaxy
    0.07
    Bro
    0.07
     ד
    0.07
    Activations Density 0.071%

    No Known Activations