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. 43165
    Prev
    Next
    INDEX
    Explanations

    not

    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
     vir
    -0.08
    575
    -0.08
     Queen
    -0.07
     biraz
    -0.07
    cool
    -0.07
     cool
    -0.07
     BEN
    -0.07
     oui
    -0.07
    Anton
    -0.07
    mens
    -0.07
    POSITIVE LOGITS
    ever
    0.08
    éid
    0.08
    oday
    0.08
    727
    0.08
     outright
    0.07
     prejudice
    0.07
    редит
    0.07
    尺
    0.07
     છું
    0.07
    TC
    0.07
    Activations Density 0.035%

    No Known Activations