© 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. 23-RESID-POST-AA
    11. 49440
    Prev
    Next
    INDEX
    Explanations

    episode

    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
     Arbeitgeber
    -0.10
     предприятия
    -0.10
     entidad
    -0.10
     підприєм
    -0.10
     vendors
    -0.10
     merchant
    -0.10
     vendor
    -0.10
     perusahaan
    -0.09
     empresa
    -0.09
     centroid
    -0.09
    POSITIVE LOGITS
     Episode
    0.38
    Episode
    0.38
     episode
    0.37
    _episode
    0.35
     episodes
    0.35
    episode
    0.34
    Episodes
    0.34
     Episodes
    0.33
    episodes
    0.33
     Season
    0.32
    Activations Density 0.143%

    No Known Activations