Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 12675
    Prev
    Next
    INDEX
    Explanations

    an

    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
     מור
    -0.09
     popula
    -0.08
     ETA
    -0.08
     dhexe
    -0.08
     শৰ
    -0.08
     סער
    -0.07
    021
    -0.07
     שפּיל
    -0.07
     tswa
    -0.07
     formaat
    -0.07
    POSITIVE LOGITS
     Floor
    0.08
    ,可
    0.08
     forget
    0.08
     Fisher
    0.08
    Floor
    0.07
     dat
    0.07
    .floor
    0.07
     floor
    0.07
     고
    0.07
    _floor
    0.07
    Activations Density 0.002%

    No Known Activations