© 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. 11-RESID-POST-AA
    11. 64804
    Prev
    Next
    INDEX
    Explanations

    Image descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     쓰
    -0.08
     Flyers
    -0.07
     Texte
    -0.07
     requirement
    -0.07
    ocument
    -0.07
     प्रद
    -0.07
     sinful
    -0.07
     Pele
    -0.07
    uen
    -0.07
     parole
    -0.07
    POSITIVE LOGITS
     hieronder
    0.11
     પ્રમાણે
    0.09
    如下
    0.09
     herein
    0.09
     મુજબ
    0.09
     illustrates
    0.09
     abaixo
    0.08
    իկ
    0.08
    goed
    0.08
     привед
    0.08
    Activations Density 0.036%

    No Known Activations