© 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. 97268
    Prev
    Next
    INDEX
    Explanations

    ab

    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
    cidas
    -0.08
     charms
    -0.08
     шәх
    -0.08
     Infant
    -0.08
     transpose
    -0.08
     Unite
    -0.08
     Flavor
    -0.08
     sams
    -0.08
    imong
    -0.08
     comuni
    -0.08
    POSITIVE LOGITS
    支
    0.08
    ts
    0.08
     मेरा
    0.07
     tombol
    0.07
    (t
    0.07
    ，我
    0.07
    Nou
    0.07
    t
    0.07
    χει
    0.07
     out
    0.07
    Activations Density 0.000%

    No Known Activations