© 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. 19-RESID-POST-AA
    11. 102613
    Prev
    Next
    INDEX
    Explanations

    text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    31
    -0.08
    andard
    -0.08
    관리
    -0.07
     siitä
    -0.07
     &:
    -0.07
    ércoles
    -0.07
    ừa
    -0.07
    oupon
    -0.07
    vents
    -0.07
     aurait
    -0.07
    POSITIVE LOGITS
     text
    0.08
     maximale
    0.08
    	text
    0.08
     우리의
    0.07
    	max
    0.07
     naszych
    0.07
     nell
    0.07
     лоз
    0.07
     wszystkich
    0.07
     текста
    0.07
    Activations Density 0.001%

    No Known Activations