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. 65156
    Prev
    Next
    INDEX
    Explanations

    to

    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
    此次
    -0.09
     लॉ
    -0.08
    日志
    -0.08
    봤
    -0.08
     פנ
    -0.08
     joints
    -0.07
     sten
    -0.07
     शहर
    -0.07
     verst
    -0.07
     esquer
    -0.07
    POSITIVE LOGITS
    angstrom
    0.09
     rij
    0.09
    :.
    0.08
     elemental
    0.08
     measured
    0.08
     averaged
    0.07
     empir
    0.07
     Molecular
    0.07
     empirical
    0.07
    scaled
    0.07
    Activations Density 0.004%

    No Known Activations