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. 77090
    Prev
    Next
    INDEX
    Explanations

    nothing

    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
     assault
    -0.08
    rg
    -0.08
     mahimong
    -0.07
     peixe
    -0.07
    効
    -0.07
     postseason
    -0.07
     Analyze
    -0.07
     deel
    -0.07
     pháp
    -0.07
    аз
    -0.07
    POSITIVE LOGITS
     congenital
    0.09
     ailments
    0.09
     Krypt
    0.09
     poucas
    0.08
    Urg
    0.08
    FUL
    0.08
    rypto
    0.08
     kj
    0.08
     poucos
    0.07
    ৃদ
    0.07
    Activations Density 0.020%

    No Known Activations