© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 49387
    Prev
    Next
    INDEX
    Explanations

    need or want

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    might
    -0.13
     you've
    -0.13
     might
    -0.12
     won't
    -0.12
     we
    -0.12
    may
    -0.12
     gives
    -0.11
     you're
    -0.11
     may
    -0.11
    giving
    -0.11
    POSITIVE LOGITS
     them
    0.16
     that
    0.15
     him
    0.12
     find
    0.12
     למצוא
    0.12
     Find
    0.12
    找到
    0.11
    	that
    0.11
     an
    0.11
    ↵↵
    0.11
    Activations Density 0.137%

    No Known Activations