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. 111982
    Prev
    Next
    INDEX
    Explanations

    fiber optic modes

    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
     ordem
    -0.10
     comerciantes
    -0.09
     merchants
    -0.08
     comercio
    -0.08
     divine
    -0.08
     political
    -0.08
     comércio
    -0.08
     children's
    -0.08
     funer
    -0.08
     lich
    -0.08
    POSITIVE LOGITS
    יגה
    0.09
    Contenido
    0.08
     विमान
    0.08
    _FAILURE
    0.08
    (sk
    0.08
     spinal
    0.08
    Ошибка
    0.08
     imperfections
    0.08
     erb
    0.07
    (S
    0.07
    Activations Density 0.004%

    No Known Activations