© 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. 91699
    Prev
    Next
    INDEX
    Explanations

    actor/character names

    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
     metu
    -0.09
    roscopic
    -0.09
     מהמ
    -0.08
     இருந்த
    -0.08
    盈
    -0.08
    akanan
    -0.08
     kubera
    -0.08
    LLU
    -0.08
    aug
    -0.08
     盈
    -0.08
    POSITIVE LOGITS
     portrayed
    0.09
    .roles
    0.09
     역할
    0.09
     roles
    0.09
     fictional
    0.09
     convinc
    0.08
     actor
    0.08
     Roles
    0.08
    roles
    0.08
     ಪಾತ್ರ
    0.08
    Activations Density 0.077%

    No Known Activations