© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 25909
    Prev
    Next
    INDEX
    Explanations

    logic statements

    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
     شهر
    -0.08
    árm
    -0.08
     finer
    -0.08
     حرارة
    -0.08
     cikin
    -0.07
     వే�
    -0.07
     سفر
    -0.07
     أر
    -0.07
     防
    -0.07
     కోసం
    -0.07
    POSITIVE LOGITS
    -count
    0.10
     Count
    0.09
     Counting
    0.09
     disabling
    0.09
    _counts
    0.09
     toggle
    0.09
    _count
    0.09
    ,count
    0.09
    _toggle
    0.09
     counting
    0.09
    Activations Density 0.016%

    No Known Activations