© 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. 23-RESID-POST-AA
    11. 51572
    Prev
    Next
    INDEX
    Explanations

    fields and farmers

    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
     nightclub
    -0.11
     nightlife
    -0.11
     रात
    -0.09
     בעיר
    -0.09
     Night
    -0.09
    Night
    -0.09
    ’hôtel
    -0.09
     nightly
    -0.09
     NIGHT
    -0.09
     notran
    -0.09
    POSITIVE LOGITS
    青青草原
    0.22
     खेत
    0.22
    青青草
    0.21
     ખેડ
    0.19
     రైత
    0.19
     meadow
    0.19
     farmer
    0.19
     farmers
    0.19
     fields
    0.19
     pasture
    0.18
    Activations Density 0.067%

    No Known Activations