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. 53285
    Prev
    Next
    INDEX
    Explanations

    Ionic

    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
    84
    -0.08
    nil
    -0.08
    ceis
    -0.08
    SECONDS
    -0.08
    MK
    -0.07
    MAR
    -0.07
    unday
    -0.07
    460
    -0.07
    adzi
    -0.07
    ichert
    -0.07
    POSITIVE LOGITS
     iyon
    0.09
     crystals
    0.09
     彩
    0.09
    彼
    0.09
     ؟↵↵
    0.09
    نية
    0.08
     PSU
    0.08
     handshake
    0.08
     amic
    0.08
     واضح
    0.08
    Activations Density 0.004%

    No Known Activations