© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 109815
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    Negative Logits
    rupted
    -0.09
     mug
    -0.08
     легко
    -0.08
    grep
    -0.08
    気
    -0.08
    chance
    -0.08
    の記事
    -0.08
     कहानी
    -0.08
     आसानी
    -0.08
     chances
    -0.07
    POSITIVE LOGITS
     Highway
    0.12
    接口
    0.11
     clk
    0.11
    (clk
    0.11
    _clk
    0.10
     highway
    0.10
    endmodule
    0.09
     Clock
    0.09
     IBOutlet
    0.09
    .Clock
    0.09
    Activations Density 0.005%

    No Known Activations