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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 56082
    Prev
    Next
    INDEX
    Explanations

    genetics and mutations

    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
     Profesor
    -0.09
     categ
    -0.08
     osp
    -0.08
     Cursos
    -0.08
    _category
    -0.08
     ao
    -0.08
     prototypes
    -0.08
    endedores
    -0.08
     contador
    -0.08
    美女
    -0.08
    POSITIVE LOGITS
     mutations
    0.10
     mutation
    0.09
     mutated
    0.09
     allele
    0.09
     रक्त
    0.08
     опух
    0.08
     आब
    0.08
     bloed
    0.08
     событий
    0.08
     epile
    0.08
    Activations Density 0.004%

    No Known Activations