© 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. 19-RESID-POST-AA
    11. 18854
    Prev
    Next
    INDEX
    Explanations

    sqrt

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (
    -0.10
     sqrt
    -0.10
     √
    -0.09
     to
    -0.08
     a
    -0.08
     and
    -0.08
    sqrt
    -0.08
     (\
    -0.08
     và
    -0.07
     στοι
    -0.07
    POSITIVE LOGITS
    }+
    0.10
    лекет
    0.10
    ңел
    0.09
     naats
    0.09
    手机在线
    0.09
    _SEND
    0.09
    దేశ్
    0.09
     Эмом
    0.09
     ինչպես
    0.09
    anglais
    0.09
    Activations Density 0.006%

    No Known Activations