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. 98278
    Prev
    Next
    INDEX
    Explanations

    declare

    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
     amount
    -0.08
    amount
    -0.08
    र्भ
    -0.07
     अवसर
    -0.07
    CTOR
    -0.07
    /messages
    -0.07
     présentant
    -0.07
     लगभग
    -0.07
     mechanism
    -0.07
    絡
    -0.07
    POSITIVE LOGITS
    enburg
    0.09
     bans
    0.09
    宴
    0.08
     bangs
    0.08
     loudly
    0.08
     resten
    0.08
     贝
    0.08
    肯
    0.08
     Anw
    0.08
     ignorance
    0.08
    Activations Density 0.018%

    No Known Activations