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

    Neuronpedia

    Jacobian LensNEW
    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. 23-RESID-POST-AA
    11. 50177
    Prev
    Next
    INDEX
    Explanations

    Assisting the user

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gaze
    -0.08
    覚
    -0.08
     ondersteuning
    -0.07
     gö
    -0.07
    oad
    -0.07
     പിന്ത
    -0.07
    Support
    -0.07
    언
    -0.07
    ――
    -0.07
    _support
    -0.07
    POSITIVE LOGITS
     જોડ
    0.08
     brid
    0.08
     demolition
    0.08
    DIM
    0.08
     bridges
    0.08
     Bord
    0.07
     تړ
    0.07
     Buick
    0.07
    分
    0.07
     HEIGHT
    0.07
    Activations Density 0.000%

    No Known Activations