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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 106214
    Prev
    Next
    INDEX
    Explanations

    aa

    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
     péri
    -0.08
    čina
    -0.08
    uckles
    -0.08
     undefeated
    -0.08
    Cert
    -0.08
     infantiles
    -0.08
     nineteenth
    -0.08
    eté
    -0.07
     Julius
    -0.07
     célib
    -0.07
    POSITIVE LOGITS
    ಂತೆ
    0.08
     occupancy
    0.07
     anbieten
    0.07
     Remember
    0.07
     facilities
    0.07
     музы
    0.07
     interpreted
    0.07
     offering
    0.07
     предостав
    0.07
    ォ
    0.07
    Activations Density 0.002%

    No Known Activations