© 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. 29585
    Prev
    Next
    INDEX
    Explanations

    alcohol percentage

    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
     Awards
    -0.09
    Awards
    -0.09
     proactive
    -0.09
    libs
    -0.08
    /Footer
    -0.08
    Award
    -0.08
     awards
    -0.08
     izquierdo
    -0.08
    arrival
    -0.08
     ಪ್ರಶ
    -0.08
    POSITIVE LOGITS
     ethanol
    0.09
     glycer
    0.09
     antise
    0.09
     hydrogen
    0.09
    เปอร์
    0.09
     disinfect
    0.09
    工业
    0.09
     ppm
    0.08
     domést
    0.08
     industrial
    0.08
    Activations Density 0.013%

    No Known Activations