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. 15-RESID-POST-AA
    6. 19738
    Prev
    Next
    INDEX
    Explanations

    Mixed text snippets

    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
    థ్యంలో
    -0.12
     ყოფილ
    -0.12
     stavanger
    -0.11
     pornofilm
    -0.11
    	this
    -0.11
     këtë
    -0.11
     tämän
    -0.11
     ovaj
    -0.11
     կունեն
    -0.11
     drammen
    -0.10
    POSITIVE LOGITS
     of
    0.10
     '
    0.10
     данные
    0.09
     -
    0.09
    only
    0.08
     данных
    0.08
     only
    0.08
     not
    0.08
     Only
    0.08
     /
    0.08
    Activations Density 0.049%

    No Known Activations