© 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. 97209
    Prev
    Next
    INDEX
    Explanations

    say the ending -illion

    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
     prestig
    -0.08
     tercer
    -0.08
     beoord
    -0.08
     kord
    -0.08
    حض
    -0.08
     voorbereid
    -0.07
     printk
    -0.07
    -thirds
    -0.07
     agrega
    -0.07
    dued
    -0.07
    POSITIVE LOGITS
    illation
    0.09
    илли
    0.09
    ंच
    0.08
    лон
    0.08
    .Top
    0.08
    xn
    0.08
    x
    0.08
     εκα
    0.07
    illion
    0.07
    천
    0.07
    Activations Density 0.000%

    No Known Activations