© 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. 2788
    Prev
    Next
    INDEX
    Explanations

    champagnes and wines

    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
     investigate
    -0.09
    bie
    -0.08
    Nos
    -0.07
     Titan
    -0.07
    Nach
    -0.07
     hedge
    -0.07
     stacked
    -0.07
     refuse
    -0.07
     rethink
    -0.07
    板
    -0.07
    POSITIVE LOGITS
     proš
    0.08
     Manc
    0.08
    onaut
    0.08
    .er
    0.07
    Vi
    0.07
    .mon
    0.07
     Rä
    0.07
    manufact
    0.07
     summers
    0.07
    _deg
    0.07
    Activations Density 0.000%

    No Known Activations