© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 1137
    Prev
    Next
    INDEX
    Explanations

    ended

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Priority
    -0.09
     Seoul
    -0.08
    	dr
    -0.08
     ત
    -0.07
    	sprite
    -0.07
    Jeg
    -0.07
     uto
    -0.07
     ferry
    -0.07
    .Process
    -0.07
     mesta
    -0.07
    POSITIVE LOGITS
    ถาม
    0.12
    質問
    0.10
     perguntas
    0.10
     rhetorical
    0.09
     conversational
    0.09
     ಪ್ರಶ್ನ
    0.09
     질문
    0.09
     প্রশ্ন
    0.09
     уточ
    0.09
     पूछ
    0.09
    Activations Density 0.010%

    No Known Activations