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. 23886
    Prev
    Next
    INDEX
    Explanations

    beans

    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
     المؤمن
    -0.09
     consenting
    -0.08
    па
    -0.08
     Account
    -0.08
     generalmente
    -0.08
    itsu
    -0.07
    which
    -0.07
     תא
    -0.07
    .team
    -0.07
    kennen
    -0.07
    POSITIVE LOGITS
     aromatic
    0.08
     aromas
    0.08
     aroma
    0.08
     atmosfer
    0.08
     جی
    0.08
    〕
    0.08
     vinyl
    0.08
     주변
    0.08
     తీ
    0.08
    �
    0.08
    Activations Density 0.009%

    No Known Activations