© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 47934
    Prev
    Next
    INDEX
    Explanations

    th

    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
     lese
    -0.08
     להצ
    -0.08
     hitta
    -0.08
     теп
    -0.08
    olicies
    -0.08
    рт
    -0.08
     ninety
    -0.08
     yahoo
    -0.08
     орт
    -0.08
    ార్ట
    -0.08
    POSITIVE LOGITS
    ang
    0.09
    称
    0.08
    bass
    0.08
    ọ
    0.08
    ुन
    0.08
    ùng
    0.07
    ụ
    0.07
    abant
    0.07
    ỏi
    0.07
    ANG
    0.07
    Activations Density 0.001%

    No Known Activations