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. 15-RESID-POST-AA
    6. 10
    Prev
    Next
    INDEX
    Explanations

    angles and slight adjustments

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     redux
    -0.08
     ren
    -0.07
     pulm
    -0.07
     lona
    -0.07
     Respublik
    -0.07
     sav
    -0.07
     mln
    -0.07
     terapia
    -0.07
     parque
    -0.07
     Respubl
    -0.07
    POSITIVE LOGITS
    -angle
    0.11
     थोड़ा
    0.10
     slightly
    0.10
     légèrement
    0.10
     вверх
    0.10
    ANGLE
    0.09
     slight
    0.09
    YAxis
    0.09
     ligeramente
    0.09
    Angle
    0.09
    Activations Density 0.005%

    No Known Activations