© 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. 111124
    Prev
    Next
    INDEX
    Explanations

    problem constraints

    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
     herzlich
    -0.08
    दर
    -0.08
     udział
    -0.08
     authent
    -0.08
     irresistible
    -0.08
    _pct
    -0.07
     "**
    -0.07
     гармони
    -0.07
     clichés
    -0.07
     verantwortlich
    -0.07
    POSITIVE LOGITS
     arbitrary
    0.08
     دیگری
    0.08
     instead
    0.08
     sit
    0.08
     موجود
    0.08
     ،
    0.08
     مثل
    0.08
     نیز
    0.08
     اضاف
    0.08
     مجموعة
    0.08
    Activations Density 0.120%

    No Known Activations