© 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. 47790
    Prev
    Next
    INDEX
    Explanations

    Period

    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
    tight
    -0.08
     teatr
    -0.07
     prod
    -0.07
    ambil
    -0.07
    teach
    -0.07
    unta
    -0.07
     siji
    -0.07
    _literals
    -0.07
    operate
    -0.07
    recommended
    -0.07
    POSITIVE LOGITS
    Volumes
    0.08
     sev
    0.08
    749
    0.08
     constamment
    0.08
     volumes
    0.07
     Illegal
    0.07
    982
    0.07
    545
    0.07
     codec
    0.07
     Volume
    0.07
    Activations Density 0.000%

    No Known Activations