© 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. 11-RESID-POST-AA
    11. 111435
    Prev
    Next
    INDEX
    Explanations

    statistical analysis

    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
    spired
    -0.09
     uphill
    -0.08
    beros
    -0.08
    chelle
    -0.08
    bern
    -0.08
     Radiation
    -0.08
    grass
    -0.08
     принос
    -0.07
    ainter
    -0.07
     Laser
    -0.07
    POSITIVE LOGITS
     descript
    0.12
     descriptive
    0.10
     respondents
    0.09
     percentages
    0.09
     literacy
    0.09
     населения
    0.09
    人口
    0.09
     statistics
    0.09
     demographic
    0.09
     statistiques
    0.09
    Activations Density 0.008%

    No Known Activations