© 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. 33
    Prev
    Next
    INDEX
    Explanations

    Martyrs

    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
     fibro
    -0.09
    hia
    -0.08
    ISTA
    -0.08
     Php
    -0.08
     efficiencies
    -0.07
     attrib
    -0.07
     ration
    -0.07
     arra
    -0.07
     Hemp
    -0.07
     Fib
    -0.07
    POSITIVE LOGITS
     ※
    0.08
     電
    0.08
    /png
    0.08
     partire
    0.07
     Last
    0.07
     delight
    0.07
    _Last
    0.07
    團
    0.07
     شر
    0.07
     absurd
    0.07
    Activations Density 0.006%

    No Known Activations