© 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. 51399
    Prev
    Next
    INDEX
    Explanations

    ob/cob

    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
    िली
    -0.08
    кін
    -0.08
    ॉक
    -0.08
     happier
    -0.08
    োখ
    -0.08
    	ON
    -0.08
    	Node
    -0.08
    	fi
    -0.07
    kning
    -0.07
     Shug
    -0.07
    POSITIVE LOGITS
    web
    0.16
    ertura
    0.15
    (web
    0.12
    _web
    0.12
    ham
    0.11
    -web
    0.11
     web
    0.10
    ras
    0.10
    blers
    0.10
    Web
    0.10
    Activations Density 0.002%

    No Known Activations