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. 23778
    Prev
    Next
    INDEX
    Explanations

    excerpts

    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
    aduras
    -0.07
     tele
    -0.07
    -0.07
     лю
    -0.07
    tele
    -0.07
    jenja
    -0.07
    	mem
    -0.07
     расход
    -0.07
     ув
    -0.07
    adura
    -0.07
    POSITIVE LOGITS
     inderdaad
    0.09
     indeed
    0.08
    上述
    0.08
    সব
    0.07
     Kais
    0.07
     genoemde
    0.07
    -mentioned
    0.07
     சீ
    0.07
     Chinese
    0.07
    וסר
    0.07
    Activations Density 1.795%

    No Known Activations