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. 27
    Prev
    Next
    INDEX
    Explanations

    Other languages for "other"

    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
    Ini
    -0.08
     keg
    -0.07
     steen
    -0.07
    leh
    -0.07
    UCK
    -0.07
    riet
    -0.07
    LEEP
    -0.07
     واخ
    -0.07
    Assigned
    -0.07
    阅
    -0.07
    POSITIVE LOGITS
     autre
    0.09
     altri
    0.09
     дагы
    0.09
     други
    0.09
    'autres
    0.09
     અન્ય
    0.08
     अन्य
    0.08
     ಮತ್ತ
    0.08
    ’autres
    0.08
    other
    0.08
    Activations Density 0.000%

    No Known Activations