© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 112600
    Prev
    Next
    INDEX
    Explanations

    blank

    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
     unf
    -0.09
     rival
    -0.08
     Wiener
    -0.08
     skjer
    -0.07
    …。
    -0.07
     gó
    -0.07
    .kn
    -0.07
    .multi
    -0.07
     MULT
    -0.07
     adap
    -0.07
    POSITIVE LOGITS
     lanes
    0.09
     kosong
    0.09
     lijnen
    0.08
     линии
    0.08
     lines
    0.08
     déjeuner
    0.08
     linha
    0.08
    ikhail
    0.08
     остров
    0.08
     Lines
    0.08
    Activations Density 0.001%

    No Known Activations