© 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. 2915
    Prev
    Next
    INDEX
    Explanations

    any

    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
     circulate
    -0.08
     erscheint
    -0.08
     aparecen
    -0.08
    cir
    -0.08
     Areas
    -0.08
     circul
    -0.08
    했고
    -0.08
     circulation
    -0.08
     habia
    -0.08
    Cir
    -0.08
    POSITIVE LOGITS
    øv
    0.07
     towel
    0.07
    �
    0.07
    ugen
    0.07
    姿
    0.07
    obby
    0.07
    ichy
    0.07
    407
    0.07
    -Clause
    0.07
     auctor
    0.07
    Activations Density 0.001%

    No Known Activations