© 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. 24650
    Prev
    Next
    INDEX
    Explanations

    Plural and groups

    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
     Elvis
    -0.08
     atent
    -0.08
    bob
    -0.07
    -0.07
    colored
    -0.07
    prepare
    -0.07
    aria
    -0.07
    jẹ
    -0.07
     Simba
    -0.07
     savon
    -0.07
    POSITIVE LOGITS
    онд
    0.09
    илиш
    0.08
     Accordion
    0.08
     usw
    0.08
    になる
    0.07
    	std
    0.07
    ASH
    0.07
     Activate
    0.07
    	unset
    0.07
     ঘোষণা
    0.07
    Activations Density 0.002%
    No Known Activations