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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 44514
    Prev
    Next
    INDEX
    Explanations

    numbers and statistics

    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
     middle
    -0.08
    clos
    -0.08
     deviations
    -0.07
     machining
    -0.07
    hana
    -0.07
     closer
    -0.07
    utility
    -0.07
     midfield
    -0.07
    middle
    -0.07
     tails
    -0.07
    POSITIVE LOGITS
     Thousands
    0.18
     duizenden
    0.18
     thousands
    0.18
     milhares
    0.18
     тысячи
    0.17
     हजार
    0.17
     ಸಾವಿರ
    0.17
     लाख
    0.16
     millions
    0.16
     dozens
    0.16
    Activations Density 0.214%

    No Known Activations