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. 98258
    Prev
    Next
    INDEX
    Explanations

    data collection

    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
     i'm
    -0.08
    _kw
    -0.08
    ్
    -0.08
     పార
    -0.08
    linewidth
    -0.08
     Ingredients
    -0.08
     пар
    -0.08
     Eco
    -0.08
     linewidth
    -0.07
    _↵
    -0.07
    POSITIVE LOGITS
     detaine
    0.13
     millions
    0.09
     torture
    0.09
     focus
    0.09
     લાખ
    0.09
     sophist
    0.09
     heg
    0.08
     lawful
    0.08
    刑
    0.08
     लाख
    0.08
    Activations Density 0.040%

    No Known Activations