© 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. 30374
    Prev
    Next
    INDEX
    Explanations

    explanations requested

    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
     Schatz
    -0.08
    -0.08
     pagamentos
    -0.08
     Herbst
    -0.08
     repent
    -0.08
    -br
    -0.08
     Brux
    -0.08
     melodic
    -0.08
     Bradley
    -0.08
     Gund
    -0.08
    POSITIVE LOGITS
     nyata
    0.08
     concret
    0.08
    Concrete
    0.08
     illustrate
    0.08
     iz
    0.08
     영
    0.07
    _IOCTL
    0.07
     က
    0.07
     isp
    0.07
     दाख
    0.07
    Activations Density 0.094%
    No Known Activations