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. 77579
    Prev
    Next
    INDEX
    Explanations

    R-squared in statistics

    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
    ाएं
    -0.08
    াক্ষ
    -0.08
     multis
    -0.07
     junction
    -0.07
     fist
    -0.07
    /apps
    -0.07
    After
    -0.07
    672
    -0.07
     disponibles
    -0.07
     prit
    -0.07
    POSITIVE LOGITS
     محافظ
    0.09
    score
    0.09
     Score
    0.09
    ämm
    0.09
    rá
    0.09
     Scores
    0.08
     คะแนน
    0.08
     Clever
    0.08
    -Control
    0.08
     UNDER
    0.08
    Activations Density 0.002%

    No Known Activations