© 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. 50773
    Prev
    Next
    INDEX
    Explanations

    abbreviations

    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
     hermoso
    -0.08
     sensual
    -0.08
    нали
    -0.08
     pleasures
    -0.08
     bowls
    -0.08
     vineyards
    -0.07
     nourishing
    -0.07
     immerse
    -0.07
     nourishment
    -0.07
     bowl
    -0.07
    POSITIVE LOGITS
     abbreviation
    0.50
     abbrevi
    0.43
     acronym
    0.43
     abbre
    0.37
     abbreviated
    0.35
     acr
    0.34
    缩
    0.33
     Acr
    0.32
     сокращ
    0.31
     abre
    0.31
    Activations Density 0.110%

    No Known Activations