© 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. 75495
    Prev
    Next
    INDEX
    Explanations

    multiple languages/translation

    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
    posto
    -0.07
    timeofday
    -0.07
    soz
    -0.07
     Ges
    -0.07
     Interstate
    -0.07
     correspond
    -0.07
     ends
    -0.07
     abat
    -0.07
     fitted
    -0.07
     migrated
    -0.07
    POSITIVE LOGITS
    _NO
    0.08
    .Unknown
    0.08
     circle
    0.07
     неизвест
    0.07
    irlər
    0.07
     CONDITIONS
    0.07
     Condition
    0.07
    arging
    0.07
    _PROPERTIES
    0.07
    	url
    0.07
    Activations Density 0.001%

    No Known Activations