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. 119329
    Prev
    Next
    INDEX
    Explanations

    that

    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
    에게
    -0.08
    Mer
    -0.08
     koht
    -0.08
     अभी
    -0.08
     सिर्फ
    -0.08
     hazard
    -0.07
    عام
    -0.07
    IZE
    -0.07
     acceptable
    -0.07
     masih
    -0.07
    POSITIVE LOGITS
     Schulter
    0.09
    	mt
    0.08
    	gb
    0.08
     предотвращ
    0.08
    pheric
    0.07
     bleu
    0.07
    	un
    0.07
     миллиард
    0.07
     Greenpeace
    0.07
    ادة
    0.07
    Activations Density 0.004%

    No Known Activations