© 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. 13251
    Prev
    Next
    INDEX
    Explanations

    non-negotiable (hyphenated)

    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
     ಪಾಲ
    -0.08
     ಮೆ
    -0.08
     nac
    -0.08
     propr
    -0.07
    nman
    -0.07
     gland
    -0.07
    лал
    -0.07
    irr
    -0.07
     chore
    -0.07
     goes
    -0.07
    POSITIVE LOGITS
     Kun
    0.08
    0.08
     Infer
    0.08
    0.07
    航
    0.07
     Sne
    0.07
    arc
    0.07
     wonders
    0.07
     Malaysia
    0.07
    amang
    0.07
    Activations Density 0.002%

    No Known Activations