© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 64993
    Prev
    Next
    INDEX
    Explanations

    Schwartz

    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
    ®,
    -0.08
     nič
    -0.08
     dėl
    -0.08
    ন্য
    -0.07
    -0.07
    ®
    -0.07
    RSA
    -0.07
     Là
    -0.07
     electrodes
    -0.07
     nabij
    -0.07
    POSITIVE LOGITS
    Football
    0.09
    .Memory
    0.09
     sın
    0.08
     구
    0.08
    aily
    0.08
     خبر
    0.08
     DAILY
    0.08
    수가
    0.07
    aint
    0.07
    .ERROR
    0.07
    Activations Density 0.000%

    No Known Activations