© 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. 23-RESID-POST-AA
    11. 51596
    Prev
    Next
    INDEX
    Explanations

    strong desire/dedication

    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
     reachable
    -0.09
     influenced
    -0.09
     complemented
    -0.08
     Things
    -0.08
     >(
    -0.08
     Included
    -0.08
     included
    -0.08
    reachable
    -0.08
     =
    -0.08
     bordered
    -0.08
    POSITIVE LOGITS
     desire
    0.25
     penchant
    0.23
     emphasis
    0.22
     willingness
    0.21
     appreciation
    0.21
     reliance
    0.21
     commitment
    0.20
     insist
    0.20
     pursuit
    0.20
     attempt
    0.19
    Activations Density 0.165%

    No Known Activations