Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 29867
    Prev
    Next
    INDEX
    Explanations

    ‑

    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
     எந்த
    -0.08
    SEE
    -0.08
     எதிர
    -0.07
     sonuc
    -0.07
    Movimiento
    -0.07
     Disconnect
    -0.07
    oth
    -0.07
    othesis
    -0.07
    HU
    -0.07
     closet
    -0.07
    POSITIVE LOGITS
    (func
    0.08
    ెక
    0.07
    丁
    0.07
     zwe
    0.07
     hora
    0.07
    DER
    0.07
     aer
    0.07
    oded
    0.07
    γέν
    0.07
     striving
    0.07
    Activations Density 0.040%

    No Known Activations