© 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. 49882
    Prev
    Next
    INDEX
    Explanations

    Benzodiazepines

    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
     Buick
    -0.09
     gce
    -0.09
    Anybody
    -0.09
     macroph
    -0.09
     poj
    -0.08
    .delegate
    -0.08
     accommod
    -0.08
     aparición
    -0.08
    Duck
    -0.08
     parada
    -0.08
    POSITIVE LOGITS
    odia
    0.12
     Anxiety
    0.11
     anxiety
    0.10
    az
    0.10
    oxetine
    0.10
     ansiedad
    0.09
    amphetamine
    0.09
    thi
    0.09
    lofen
    0.09
     mood
    0.09
    Activations Density 0.003%

    No Known Activations