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

    Neuronpedia

    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. 47672
    Prev
    Next
    INDEX
    Explanations

    s

    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
     paralysis
    -0.08
     지
    -0.08
     Hogan
    -0.08
     способности
    -0.08
     której
    -0.08
     Conselho
    -0.07
    _contains
    -0.07
     single
    -0.07
    .Member
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     alles
    0.09
    everything
    0.08
    wine
    0.08
     dae
    0.08
     unsur
    0.08
     coop
    0.08
     everything
    0.08
     Everything
    0.08
     всё
    0.08
    فيد
    0.08
    Activations Density 0.000%

    No Known Activations