© 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. 95646
    Prev
    Next
    INDEX
    Explanations

    final

    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
     infinit
    -0.08
     minimally
    -0.08
     structured
    -0.08
     стимули
    -0.08
     Meh
    -0.07
     trì
    -0.07
     emblem
    -0.07
    บุ
    -0.07
     arranc
    -0.07
     znač
    -0.07
    POSITIVE LOGITS
    -worthy
    0.09
    arei
    0.08
    ocyt
    0.08
    occo
    0.08
     तयारी
    0.08
    !↵
    0.08
     Smash
    0.07
    ify
    0.07
     nhé
    0.07
    theros
    0.07
    Activations Density 0.008%

    No Known Activations