© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 49073
    Prev
    Next
    INDEX
    Explanations

    seud

    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
     recreational
    -0.08
    	parse
    -0.08
     sections
    -0.08
     stereotypes
    -0.08
    .sections
    -0.08
    ानी
    -0.07
     phrases
    -0.07
     museum
    -0.07
     শিল্প
    -0.07
     reputation
    -0.07
    POSITIVE LOGITS
    'inter
    0.08
     febrero
    0.08
    attan
    0.08
     нех
    0.08
    ungsver
    0.08
    fts
    0.08
    Interstitial
    0.08
     blasted
    0.08
    mons
    0.08
    arth
    0.08
    Activations Density 0.000%

    No Known Activations