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. 88209
    Prev
    Next
    INDEX
    Explanations

    Unknown quantity

    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
     מר
    -0.08
     반
    -0.08
     Кавказ
    -0.08
    야
    -0.07
    ivik
    -0.07
    igny
    -0.07
     Pup
    -0.07
     Sert
    -0.07
    UNDLE
    -0.07
     rechazo
    -0.07
    POSITIVE LOGITS
     unspecified
    0.10
    是多少
    0.10
    $value
    0.09
     qualifier
    0.09
     synonyms
    0.09
     multiples
    0.09
    entionally
    0.09
     неоп
    0.09
     dollars
    0.09
     quantified
    0.08
    Activations Density 0.038%

    No Known Activations