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. 90723
    Prev
    Next
    INDEX
    Explanations

    fractions and 1

    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
     stored
    -0.09
     milestones
    -0.07
     мор
    -0.07
    Stored
    -0.07
     저장
    -0.07
     starting
    -0.07
     Stored
    -0.07
     suht
    -0.07
     armazen
    -0.06
     itib
    -0.06
    POSITIVE LOGITS
     partecip
    0.09
     contributions
    0.09
     Contributions
    0.09
     individually
    0.09
     contrib
    0.09
     deelnemen
    0.09
    öff
    0.09
    Contribution
    0.09
    fø
    0.09
    ెక్క
    0.09
    Activations Density 0.061%

    No Known Activations