© 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. 2706
    Prev
    Next
    INDEX
    Explanations

    this

    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
    spots
    -0.09
     Columbia
    -0.08
     Freder
    -0.08
     Lana
    -0.08
     speaks
    -0.07
     falle
    -0.07
     Gus
    -0.07
     spots
    -0.07
     Jos
    -0.07
     oe
    -0.07
    POSITIVE LOGITS
    אמ
    0.09
     अम
    0.08
    (metadata
    0.08
     Trem
    0.07
    .operations
    0.07
     igualdade
    0.07
     ам
    0.07
     dermatitis
    0.07
    渡
    0.07
     Wine
    0.07
    Activations Density 0.000%

    No Known Activations