© 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. 23-RESID-POST-AA
    11. 47886
    Prev
    Next
    INDEX
    Explanations

    Code with annotations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ებელი
    -0.10
     '".
    -0.10
    ავალი
    -0.09
    ებელია
    -0.09
     kuita
    -0.09
     स्वर
    -0.09
    ()%
    -0.09
     ტიპ
    -0.09
    ებლ
    -0.09
     ffordd
    -0.09
    POSITIVE LOGITS
    0.16
     @
    0.15
    	UPROPERTY
    0.11
    @Many
    0.11
    @Mapper
    0.11
    @Bean
    0.10
    @Setter
    0.09
    @Get
    0.09
     &#
    0.09
    @Autowired
    0.09
    Activations Density 0.006%

    No Known Activations