© 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. 47717
    Prev
    Next
    INDEX
    Explanations

    oni

    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
    _plan
    -0.09
    optimal
    -0.08
     Optimal
    -0.08
    Optimal
    -0.08
    optim
    -0.08
    more
    -0.08
    mass
    -0.07
    ക്രമ
    -0.07
     retard
    -0.07
     Mega
    -0.07
    POSITIVE LOGITS
    żs
    0.11
    żej
    0.11
    童
    0.08
     διαφορε
    0.08
    েলায়
    0.08
    েজ
    0.08
    ędzy
    0.08
    党员
    0.08
     vek
    0.08
     scrub
    0.07
    Activations Density 0.000%

    No Known Activations