© 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. 91227
    Prev
    Next
    INDEX
    Explanations

    lava

    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
     stakeholders
    -0.10
     stakeholder
    -0.09
     na
    -0.08
     naive
    -0.08
    ส่ง
    -0.07
     Stake
    -0.07
     रिल
    -0.07
     mess
    -0.07
     nause
    -0.07
     factor
    -0.07
    POSITIVE LOGITS
    joner
    0.08
     TORT
    0.08
    awed
    0.08
     Behind
    0.08
    hell
    0.08
    Behind
    0.08
    624
    0.08
    纹
    0.08
     siding
    0.07
     impressed
    0.07
    Activations Density 0.004%

    No Known Activations