© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 18919
    Prev
    Next
    INDEX
    Explanations

    motion

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chiropractic
    -0.09
    OSP
    -0.08
     oppervl
    -0.08
     powierz
    -0.08
     Remodeling
    -0.08
     OECD
    -0.08
    .objectweb
    -0.08
    øndelag
    -0.08
    ICOM
    -0.08
     Face
    -0.08
    POSITIVE LOGITS
     blur
    0.14
     trails
    0.14
     streak
    0.12
    blur
    0.11
    /bl
    0.11
    Blur
    0.11
     Trails
    0.10
     blurred
    0.10
     Blur
    0.10
     trail
    0.10
    Activations Density 0.001%

    No Known Activations