Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 55301
    Prev
    Next
    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فرصة
    -0.09
     Everyone
    -0.09
     Lotto
    -0.09
     Weekend
    -0.08
     Freunde
    -0.08
    Everyone
    -0.08
     Kaya
    -0.08
     Everybody
    -0.08
     vow
    -0.08
    Everybody
    -0.08
    POSITIVE LOGITS
    स्थ
    0.08
     asym
    0.08
    轴
    0.08
     COMP
    0.08
     sqrt
    0.08
    施
    0.07
     junction
    0.07
     divided
    0.07
     доб
    0.07
     asymmetric
    0.07
    Activations Density 0.028%

    No Known Activations