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. 112993
    Prev
    Next
    INDEX
    Explanations

    Period

    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
    -Version
    -0.09
     Rég
    -0.08
     kilom
    -0.08
    ’.
    -0.08
    Enchant
    -0.07
    ’
    -0.07
     Pric
    -0.07
     Version
    -0.07
    ဝ
    -0.07
     масса
    -0.07
    POSITIVE LOGITS
     decorate
    0.09
    shuffle
    0.08
    裸
    0.08
     answer
    0.08
     hvilket
    0.08
    unstyled
    0.08
     ANSW
    0.08
     juuri
    0.07
    SIGNED
    0.07
    ляется
    0.07
    Activations Density 0.001%

    No Known Activations