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. 113918
    Prev
    Next
    INDEX
    Explanations

    The

    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
     fruitful
    -0.07
    /her
    -0.07
    ...).
    -0.07
     ap
    -0.07
     facets
    -0.07
     ancestral
    -0.07
    स्थ
    -0.07
    伟
    -0.07
    коп
    -0.07
     wise
    -0.07
    POSITIVE LOGITS
     schlagen
    0.08
    ביע
    0.08
     STDCALL
    0.08
     Apparel
    0.08
     Dona
    0.08
    -Disposition
    0.08
     visualizar
    0.08
    ’Esp
    0.07
     DEALINGS
    0.07
     Plaintiff
    0.07
    Activations Density 0.098%

    No Known Activations