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. 52890
    Prev
    Next
    INDEX
    Explanations

    NVIDIA

    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
     inherited
    -0.09
    needle
    -0.08
    ani
    -0.08
    оч
    -0.08
    	redirect
    -0.08
    eya
    -0.08
    atin
    -0.07
     explained
    -0.07
     evidente
    -0.07
     explanatory
    -0.07
    POSITIVE LOGITS
     नवीन
    0.08
     känna
    0.08
     सक्षम
    0.08
    wei
    0.08
     ub
    0.07
     UIL
    0.07
     garanti
    0.07
     seasoning
    0.07
     counterparts
    0.07
    عمل
    0.07
    Activations Density 0.005%

    No Known Activations