© 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. 3-RESID-POST-AA
    11. 1082
    Prev
    Next
    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stumbled
    -0.08
     خر
    -0.08
     aborted
    -0.07
     celle
    -0.07
     تواجه
    -0.07
    	sw
    -0.07
    coes
    -0.07
    ière
    -0.07
     produkt
    -0.07
    	Map
    -0.07
    POSITIVE LOGITS
     Silver
    0.07
    niku
    0.07
    ct
    0.07
    _ct
    0.07
    ;"><?
    0.07
    Virtual
    0.07
    silver
    0.07
    ësh
    0.07
    507
    0.07
     silver
    0.07
    Activations Density 0.023%

    No Known Activations