© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 25222
    Prev
    Next
    INDEX
    Explanations

    1

    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
     dreadful
    -0.08
     acelerar
    -0.07
    lhe
    -0.07
     '#
    -0.07
     '|
    -0.07
    nne
    -0.07
    opolitan
    -0.07
     �
    -0.07
    ########
    -0.07
    ètres
    -0.07
    POSITIVE LOGITS
     experiencing
    0.08
     иш
    0.08
     чув
    0.08
    .study
    0.07
     tal
    0.07
     poc
    0.07
     واحدة
    0.07
     području
    0.07
     fark
    0.07
    -direction
    0.07
    Activations Density 0.001%

    No Known Activations