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

    Neuronpedia

    APICircuit 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. 88260
    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_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wobei
    -0.09
     bedeutet
    -0.08
     treated
    -0.08
     Factors
    -0.08
    சி
    -0.08
     Deshalb
    -0.08
    ete
    -0.07
     (+
    -0.07
     Κυ
    -0.07
    treated
    -0.07
    POSITIVE LOGITS
    ️
    0.09
    ème
    0.08
    卒
    0.08
    ে
    0.08
     અધ
    0.08
     जिन
    0.07
    ------------↵
    0.07
     mounts
    0.07
     folder
    0.07
    ématiques
    0.07
    Activations Density 0.002%

    No Known Activations