© 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. 3-RESID-POST-AA
    11. 2726
    Prev
    Next
    INDEX
    Explanations

    bars

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lyn
    -0.09
     attrib
    -0.08
     conscient
    -0.08
     zə
    -0.08
     chacune
    -0.08
    _nb
    -0.08
     celui
    -0.08
    UMB
    -0.07
    ARES
    -0.07
    uon
    -0.07
    POSITIVE LOGITS
     Perr
    0.08
    工
    0.08
    )!
    0.08
     decre
    0.08
    行政
    0.07
     spraw
    0.07
    .amazon
    0.07
     sprawling
    0.07
    @implementation
    0.07
    _overlap
    0.07
    Activations Density 0.001%

    No Known Activations