© 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. 71323
    Prev
    Next
    INDEX
    Explanations

    defining phrases

    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
     eind
    -0.08
     expos
    -0.08
     دهد
    -0.08
     کند
    -0.08
    ப்
    -0.07
     fuese
    -0.07
     ʻaʻole
    -0.07
     desal
    -0.07
     предусматри
    -0.07
     заканч
    -0.07
    POSITIVE LOGITS
     presumably
    0.15
     apparently
    0.12
     sicherlich
    0.12
     möglicherweise
    0.11
     vermutlich
    0.11
     probablement
    0.11
     hopefully
    0.11
    Probably
    0.11
     probably
    0.10
     likely
    0.10
    Activations Density 0.390%

    No Known Activations