© 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. 13214
    Prev
    Next
    INDEX
    Explanations

    code and math

    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
     concession
    -0.08
     Princip
    -0.07
    /pi
    -0.07
     operates
    -0.07
     fà
    -0.07
    ception
    -0.07
     опера
    -0.07
     mister
    -0.07
     operate
    -0.07
    pi
    -0.07
    POSITIVE LOGITS
    heated
    0.08
     చేసిన
    0.08
     renovated
    0.07
    自身
    0.07
     Arbeitsplatz
    0.07
     강화
    0.07
     MSI
    0.07
     �
    0.07
     Dara
    0.07
     vriendin
    0.07
    Activations Density 0.000%

    No Known Activations