© 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. 26410
    Prev
    Next
    INDEX
    Explanations

    relevant

    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
    ace
    -0.08
    283
    -0.07
     Ming
    -0.07
     sakin
    -0.07
     ಗುರು
    -0.07
     liger
    -0.07
     Tab
    -0.07
     आल
    -0.07
    -Out
    -0.07
    ople
    -0.07
    POSITIVE LOGITS
     relevant
    0.14
     relevance
    0.13
    Relevant
    0.13
     pertinent
    0.12
     aansluiten
    0.11
     relevante
    0.11
     Relevant
    0.11
     overlap
    0.10
     pertin
    0.10
     intersect
    0.10
    Activations Density 0.044%

    No Known Activations