© 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. 23-RESID-POST-AA
    11. 47908
    Prev
    Next
    INDEX
    Explanations

    polarization

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fugit
    -0.10
     relocating
    -0.09
     suburb
    -0.09
     moat
    -0.08
     relocate
    -0.08
    totime
    -0.08
    .slug
    -0.08
     priced
    -0.08
     enterr
    -0.08
     permalink
    -0.08
    POSITIVE LOGITS
     polarization
    0.33
     polarized
    0.28
     Polar
    0.27
    Polar
    0.27
    polar
    0.26
     polar
    0.26
     bire
    0.19
     orientations
    0.17
     polarity
    0.17
     orientation
    0.16
    Activations Density 0.009%

    No Known Activations