© 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. 6384
    Prev
    Next
    INDEX
    Explanations

    mathematical calculation

    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
    मी
    -0.08
    SW
    -0.08
    Swift
    -0.08
     SWE
    -0.08
     HU
    -0.08
    _SW
    -0.08
     SHO
    -0.07
    ohu
    -0.07
     IU
    -0.07
    El
    -0.07
    POSITIVE LOGITS
    	yield
    0.08
     Krak
    0.08
     tslib
    0.08
     Ankara
    0.07
    τρο
    0.07
     tri
    0.07
     заявки
    0.07
     moch
    0.07
     Nts
    0.07
    ikken
    0.07
    Activations Density 0.123%

    No Known Activations