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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 95444
    Prev
    Next
    INDEX
    Explanations

    society

    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
     合
    -0.08
     tempfile
    -0.08
     علاقے
    -0.08
    合
    -0.08
    olone
    -0.08
    quil
    -0.08
     승인
    -0.07
     department
    -0.07
     �
    -0.07
     ಪ್ರದೇಶ
    -0.07
    POSITIVE LOGITS
     ev
    0.09
    	ev
    0.08
     monarch
    0.08
     conspir
    0.07
     രൂപ
    0.07
     hij
    0.07
     namens
    0.07
     masterm
    0.07
    Hex
    0.07
     vow
    0.07
    Activations Density 0.009%

    No Known Activations