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. 111949
    Prev
    Next
    INDEX
    Explanations

    by

    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
     Apt
    -0.09
     treg
    -0.08
    ホーム
    -0.08
     Blur
    -0.08
     rpm
    -0.08
    (bl
    -0.08
     kt
    -0.08
     Goldberg
    -0.07
    」を
    -0.07
     demor
    -0.07
    POSITIVE LOGITS
    ความ
    0.10
     lack
    0.09
     circumstance
    0.08
     việc
    0.08
     możliwość
    0.08
     adanya
    0.08
     falta
    0.07
     możliwości
    0.07
     manufacturer's
    0.07
     generosity
    0.07
    Activations Density 0.033%

    No Known Activations