© 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 EvalsExportsinterp-engineNEWAPI 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. 50490
    Prev
    Next
    INDEX
    Explanations

    Communication devices

    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
    买彩票
    -0.09
     signatures
    -0.09
     ગણ
    -0.08
    озна
    -0.08
    Alphabet
    -0.08
     Verpack
    -0.08
     марки
    -0.08
     ऋ
    -0.08
     cariño
    -0.08
     ಗಣ
    -0.08
    POSITIVE LOGITS
     inter
    0.18
     headset
    0.16
     PA
    0.13
     speaker
    0.13
     Inter
    0.13
     earbuds
    0.12
     communicator
    0.12
     walk
    0.12
    inter
    0.12
    Inter
    0.12
    Activations Density 0.021%

    No Known Activations