Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 12199
    Prev
    Next
    INDEX
    Explanations

    code configuration

    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
     astronom
    -0.10
     Hale
    -0.10
     astronomy
    -0.09
     Ancient
    -0.09
     Macintosh
    -0.09
     extrater
    -0.09
     gale
    -0.09
     amateur
    -0.09
     Heavenly
    -0.09
     astronomical
    -0.09
    POSITIVE LOGITS
    Autowired
    0.19
    .springframework
    0.16
    @Bean
    0.16
     springfox
    0.16
    @Enable
    0.15
    @Configuration
    0.15
    (Spring
    0.15
    @Autowired
    0.15
    Swagger
    0.15
    @Service
    0.15
    Activations Density 0.039%

    No Known Activations