© 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. 3-RESID-POST-AA
    11. 2736
    Prev
    Next
    INDEX
    Explanations

    ,..

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     измен
    -0.09
     Han
    -0.09
     duch
    -0.08
     aport
    -0.07
    Han
    -0.07
     uc
    -0.07
     DY
    -0.07
    ران
    -0.07
     ört
    -0.07
     Elena
    -0.07
    POSITIVE LOGITS
    ADI
    0.08
    (ad
    0.08
    �
    0.08
    adili
    0.07
     �
    0.07
     بما
    0.07
     называ
    0.07
     நே
    0.07
    corr
    0.07
    mals
    0.07
    Activations Density 0.017%

    No Known Activations