© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30281
    Prev
    Next
    INDEX
    Explanations

    usion

    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
    -0.07
     �
    -0.07
     via
    -0.07
    [in
    -0.07
     富
    -0.07
    624
    -0.07
    阪
    -0.07
     സംഭവ
    -0.07
     több
    -0.07
     terjadi
    -0.07
    POSITIVE LOGITS
    igil
    0.09
    eir
    0.08
     ukup
    0.08
    зак
    0.08
    LA
    0.08
     Rush
    0.08
    OVE
    0.08
     maquinaria
    0.07
     Ergo
    0.07
     Rebel
    0.07
    Activations Density 0.000%
    No Known Activations