© 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. 7-RESID-POST-AA
    11. 761
    Prev
    Next
    INDEX
    Explanations

    incentive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nub
    -0.08
     Conv
    -0.07
    Ahead
    -0.07
    Conv
    -0.07
     Mets
    -0.07
    拾
    -0.07
    夹
    -0.07
     Essential
    -0.07
    �
    -0.07
     mad
    -0.07
    POSITIVE LOGITS
    드립니다
    0.08
     transcend
    0.08
     rebates
    0.08
    ILO
    0.08
    措施
    0.08
     vn
    0.07
     dong
    0.07
     keuntungan
    0.07
     현
    0.07
    lauf
    0.07
    Activations Density 0.004%

    No Known Activations