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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 130910
    Prev
    Next
    INDEX
    Explanations

    variations of "considered"

    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
    .need
    -0.08
     możliwości
    -0.07
    yor
    -0.07
    iyor
    -0.07
    .mine
    -0.07
    Thankfully
    -0.07
     ------------------------------------------------------------------------------------------------
    -0.07
    .ask
    -0.06
     adanya
    -0.06
    …the
    -0.06
    POSITIVE LOGITS
     considered
    0.57
     considéré
    0.53
     considerado
    0.51
     considerada
    0.50
     considerados
    0.49
     consideradas
    0.47
     dianggap
    0.47
     regarded
    0.45
     beschouwd
    0.42
     считается
    0.40
    Activations Density 0.320%

    No Known Activations