© 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. 1185
    Prev
    Next
    INDEX
    Explanations

    son/conson

    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
     sitcom
    -0.08
    xfb
    -0.07
     Raymond
    -0.07
    满意
    -0.07
     blinds
    -0.07
    wydd
    -0.07
     Mari
    -0.07
     Hermione
    -0.07
    cite
    -0.07
     sightseeing
    -0.07
    POSITIVE LOGITS
     conson
    0.10
    -ending
    0.09
     pronunciation
    0.08
    Ending
    0.08
     Ending
    0.08
     endings
    0.08
     swallowed
    0.08
     vowel
    0.08
     अक्ष
    0.08
     poisoning
    0.08
    Activations Density 0.004%

    No Known Activations