© 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 EvalsExportsinterp-engineNEWAPI 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. 110503
    Prev
    Next
    INDEX
    Explanations

    descriptive prose

    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
     perceb
    -0.09
     aparentemente
    -0.09
    Css
    -0.08
     apparently
    -0.08
     conversar
    -0.08
     observar
    -0.08
    Apparently
    -0.07
     supposedly
    -0.07
     rundt
    -0.07
     категории
    -0.07
    POSITIVE LOGITS
    骗局
    0.12
    骗局吗
    0.11
     scams
    0.10
     typo
    0.10
    处分
    0.09
     scam
    0.09
     prank
    0.08
    诈骗
    0.08
     mistake
    0.08
     mistakes
    0.08
    Activations Density 0.051%

    No Known Activations