© 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. 95791
    Prev
    Next
    INDEX
    Explanations

    notice

    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
    チ
    -0.09
     total
    -0.08
    (total
    -0.07
     da
    -0.07
     HP
    -0.07
     م
    -0.07
     naive
    -0.07
     Aff
    -0.07
    團
    -0.07
    IPO
    -0.07
    POSITIVE LOGITS
     tullut
    0.09
     tulee
    0.09
     gweith
    0.08
     చద
    0.08
    attaa
    0.08
     exe
    0.08
     …
    0.08
     enhver
    0.08
     wint
    0.08
     ტექ
    0.08
    Activations Density 0.001%

    No Known Activations