© 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. 11-RESID-POST-AA
    11. 108816
    Prev
    Next
    INDEX
    Explanations

    micro-learning

    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
    mac
    -0.08
     unchanged
    -0.08
     modulus
    -0.07
     mac
    -0.07
     must
    -0.07
    urface
    -0.07
     different
    -0.07
     alqu
    -0.07
    198
    -0.07
    199
    -0.07
    POSITIVE LOGITS
     Digest
    0.10
    digest
    0.10
     cravings
    0.10
     digest
    0.10
     cibl
    0.09
    .coroutines
    0.09
     doses
    0.09
     einzelne
    0.09
     cognit
    0.09
    igest
    0.09
    Activations Density 0.018%

    No Known Activations