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. 102998
    Prev
    Next
    INDEX
    Explanations

    Mediterranean

    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
    	fi
    -0.08
    	
    -0.08
     STATUS
    -0.08
    	h
    -0.07
     heeft
    -0.07
    	p
    -0.07
     QName
    -0.07
    _STATUS
    -0.07
    .h
    -0.07
     fi
    -0.07
    POSITIVE LOGITS
     diets
    0.10
     Intake
    0.10
    recommend
    0.09
     evidencia
    0.09
     recommendations
    0.09
    推荐
    0.09
     ketogenic
    0.09
     recomand
    0.09
    추천
    0.09
    Turkey
    0.09
    Activations Density 0.004%

    No Known Activations