Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 54962
    Prev
    Next
    INDEX
    Explanations

    lengthy text

    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
     Mostly
    -0.08
     hauptsächlich
    -0.08
     بأنها
    -0.08
    六合
    -0.08
     ech
    -0.08
     zunächst
    -0.08
    stellt
    -0.07
    Remarks
    -0.07
     Lahore
    -0.07
    udent
    -0.07
    POSITIVE LOGITS
     Deshalb
    0.08
     evidenced
    0.08
    なので
    0.08
     لذا
    0.08
    ,所以
    0.08
     vuestro
    0.08
     Derfor
    0.08
     לכן
    0.08
    だから
    0.08
     इसलिए
    0.08
    Activations Density 0.350%

    No Known Activations