© 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. 49887
    Prev
    Next
    INDEX
    Explanations

    /

    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
     Schwanz
    -0.08
     tato
    -0.08
     pastel
    -0.08
    ెస్ట్
    -0.08
     jina
    -0.07
     Judith
    -0.07
     coins
    -0.07
     honderd
    -0.07
    ego
    -0.07
     seconden
    -0.07
    POSITIVE LOGITS
     alerts
    0.08
    _alert
    0.08
    Orbit
    0.08
    alert
    0.08
     alert
    0.07
    Alerts
    0.07
    programm
    0.07
    Alert
    0.07
     programmable
    0.07
     Orbit
    0.07
    Activations Density 0.001%

    No Known Activations