© 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. 3-RESID-POST-AA
    11. 963
    Prev
    Next
    INDEX
    Explanations

    for

    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
     stretched
    -0.09
     stretching
    -0.09
     tilby
    -0.08
    幅
    -0.08
    stretch
    -0.08
     surprising
    -0.07
    _ATTRIBUTES
    -0.07
     הער
    -0.07
     studio
    -0.07
     dzień
    -0.07
    POSITIVE LOGITS
    oe
    0.09
     hired
    0.09
     ох
    0.08
     Hire
    0.08
     от
    0.07
     الذات
    0.07
     воз
    0.07
     snar
    0.07
     thief
    0.07
     despe
    0.07
    Activations Density 0.022%

    No Known Activations