© 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. 19-RESID-POST-AA
    11. 18779
    Prev
    Next
    INDEX
    Explanations

    status

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     destabil
    -0.09
    \Seeder
    -0.09
     financiamento
    -0.09
     tightened
    -0.08
     tightening
    -0.08
     азарт
    -0.08
    一等奖
    -0.08
     tilfeld
    -0.08
    _hist
    -0.07
     Patricia
    -0.07
    POSITIVE LOGITS
     статус
    0.14
    -status
    0.14
     status
    0.14
    Status
    0.14
     statuses
    0.14
    _status
    0.13
     Status
    0.13
    status
    0.13
     aangeven
    0.13
    	status
    0.13
    Activations Density 0.008%

    No Known Activations