Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 112043
    Prev
    Next
    INDEX
    Explanations

    they

    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
    "We
    -0.08
     salaire
    -0.08
    �
    -0.07
     Waist
    -0.07
     waist
    -0.07
    /storage
    -0.07
     Pkw
    -0.07
    KD
    -0.07
     wardrobe
    -0.07
    .'/'.$
    -0.07
    POSITIVE LOGITS
    phans
    0.09
     उनमें
    0.08
    0.08
     вовсе
    0.07
     …↵↵
    0.07
    oby
    0.07
     вообще
    0.07
     simply
    0.07
    ид
    0.07
     exotic
    0.07
    Activations Density 0.123%

    No Known Activations