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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 102815
    Prev
    Next
    INDEX
    Explanations

    period character

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cereal
    -0.08
     blackberry
    -0.08
     lever
    -0.07
     soybean
    -0.07
    @All
    -0.07
    }@
    -0.07
    /UIKit
    -0.07
     bula
    -0.07
    @y
    -0.07
    ,@
    -0.07
    POSITIVE LOGITS
     warme
    0.09
    ২২
    0.08
     với
    0.08
    １４
    0.08
    ственная
    0.08
    	with
    0.08
    ۴
    0.08
     پاڪ
    0.08
     puertas
    0.08
    isana
    0.08
    Activations Density 0.002%

    No Known Activations