© 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. 24943
    Prev
    Next
    INDEX
    Explanations

    formal grammars

    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
    Equals
    -0.08
    .Pod
    -0.07
     જગ
    -0.07
    这种
    -0.07
    entlichen
    -0.07
    DOB
    -0.07
    球队
    -0.07
    Tipo
    -0.07
    Minus
    -0.07
    然后
    -0.07
    POSITIVE LOGITS
     collaborations
    0.09
     الرسمية
    0.09
     collaboration
    0.09
     Collaboration
    0.09
     collabor
    0.09
     Collabor
    0.08
     сотруднич
    0.08
     अह
    0.08
     Erg
    0.08
    -sharing
    0.08
    Activations Density 0.001%

    No Known Activations