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. 29942
    Prev
    Next
    INDEX
    Explanations

    stopwords

    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
     medications
    -0.08
    check
    -0.07
     Ler
    -0.07
     medication
    -0.07
    Exercises
    -0.07
    .Low
    -0.07
    low
    -0.07
     warranted
    -0.07
    REDIT
    -0.07
    Policies
    -0.07
    POSITIVE LOGITS
     ultime
    0.09
    ųjų
    0.09
     الجميل
    0.08
     cotidiano
    0.08
     sublime
    0.08
     cotid
    0.08
     intemp
    0.08
     সুন্দর
    0.08
     reino
    0.08
     прекрасно
    0.08
    Activations Density 0.061%

    No Known Activations