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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 94814
    Prev
    Next
    INDEX
    Explanations

    programs

    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
     ಕಂಡ
    -0.07
     ವಿಜ
    -0.07
    िष
    -0.07
     ವಿಚಾರ
    -0.07
    ага
    -0.07
     MI
    -0.07
     verta
    -0.07
    irea
    -0.07
     ಶಾಲ
    -0.07
    ед
    -0.07
    POSITIVE LOGITS
    .opacity
    0.09
     Europeans
    0.08
    .longitude
    0.08
     lank
    0.08
    โม
    0.08
     wolle
    0.08
    bos
    0.08
     Dirk
    0.08
     sits
    0.08
    ovs
    0.07
    Activations Density 0.000%

    No Known Activations