© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 97270
    Prev
    Next
    INDEX
    Explanations

    Soviet Union leaders

    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
     lying
    -0.08
    WINDOW
    -0.08
     einn
    -0.08
     suíte
    -0.08
    套
    -0.07
     yardımcı
    -0.07
     possesses
    -0.07
     suite
    -0.07
     lie
    -0.07
    覆
    -0.07
    POSITIVE LOGITS
     Schip
    0.09
    umbuhan
    0.08
     Bamb
    0.08
     Jane
    0.07
    typeparam
    0.07
     Stefan
    0.07
    alten
    0.07
     VIH
    0.07
     MRI
    0.07
    ofil
    0.07
    Activations Density 0.002%

    No Known Activations