© 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. 19-RESID-POST-AA
    11. 102342
    Prev
    Next
    INDEX
    Explanations

    we

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    计
    -0.08
     accounting
    -0.08
     כשה
    -0.08
     ಸಂಖ್ಯೆ
    -0.08
     accounted
    -0.08
     stør
    -0.08
     संख्या
    -0.08
     número
    -0.07
     саны
    -0.07
     performance
    -0.07
    POSITIVE LOGITS
     derive
    0.20
     derived
    0.19
     derives
    0.19
    derive
    0.18
     ded
    0.18
     deriving
    0.18
     Derived
    0.17
    derived
    0.17
     inferred
    0.16
     consequences
    0.16
    Activations Density 0.090%

    No Known Activations