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. 78136
    Prev
    Next
    INDEX
    Explanations

    accessible from any location

    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
    platten
    -0.08
     Jungen
    -0.08
    lament
    -0.07
     ASTM
    -0.07
     STDERR
    -0.07
     propos
    -0.07
    146
    -0.07
     YY
    -0.07
    inclusive
    -0.07
     TT
    -0.07
    POSITIVE LOGITS
     Anywhere
    0.14
     Anytime
    0.13
     anywhere
    0.13
     anytime
    0.12
     überall
    0.12
    Anywhere
    0.12
     어디
    0.11
     jederzeit
    0.11
    地点
    0.10
     đâu
    0.10
    Activations Density 0.029%

    No Known Activations