© 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. 11-RESID-POST-AA
    11. 63877
    Prev
    Next
    INDEX
    Explanations

    macro photography

    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
    .Volume
    -0.09
     содержащ
    -0.08
     prominently
    -0.08
    中央
    -0.08
     randomly
    -0.08
     vaguely
    -0.08
     Lobby
    -0.08
     NYC
    -0.08
     ympär
    -0.07
     Originally
    -0.07
    POSITIVE LOGITS
     compost
    0.08
     hobbies
    0.08
     companionship
    0.08
     accessories
    0.08
     aanmerking
    0.08
     arbeiten
    0.08
     hobby
    0.08
    والی
    0.08
     comics
    0.08
     shoes
    0.08
    Activations Density 0.002%

    No Known Activations