© 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 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. 113763
    Prev
    Next
    INDEX
    Explanations

    antennas

    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
     flowing
    -0.09
     흐
    -0.08
     remembered
    -0.08
     mortality
    -0.08
    川
    -0.08
     기억
    -0.08
     데
    -0.08
     slipping
    -0.08
     accountability
    -0.07
     entertainment
    -0.07
    POSITIVE LOGITS
     antennas
    0.15
     antenna
    0.13
     Standort
    0.11
     impedance
    0.11
     Outdoor
    0.09
    Outdoor
    0.09
     tuner
    0.09
     wlan
    0.09
     transmitter
    0.09
    0.09
    Activations Density 0.012%
    No Known Activations