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. 130309
    Prev
    Next
    INDEX
    Explanations

    languages

    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
     AVC
    -0.08
     capacitor
    -0.07
    budget
    -0.07
    'use
    -0.07
     |>
    -0.07
    ffect
    -0.07
    'all
    -0.07
    scheduler
    -0.07
     inside
    -0.07
    -0.07
    POSITIVE LOGITS
     Romance
    0.10
    Latin
    0.09
     lengua
    0.09
     լեզ
    0.09
     langues
    0.09
     idioma
    0.09
    ประเทศ
    0.09
    欧洲
    0.09
     idiomas
    0.09
    Portugu
    0.08
    Activations Density 0.022%

    No Known Activations