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. 78512
    Prev
    Next
    INDEX
    Explanations

    of

    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
    (Configuration
    -0.08
    -0.08
     IMPORTANT
    -0.08
    aneous
    -0.08
    paged
    -0.08
    Feign
    -0.08
    ద
    -0.08
    important
    -0.07
    డం
    -0.07
    nal
    -0.07
    POSITIVE LOGITS
    Bird
    0.08
     quartz
    0.08
     hunter
    0.08
    Hunter
    0.08
     fiberglass
    0.08
     energi
    0.08
     clay
    0.08
     wonder
    0.07
     lekk
    0.07
     Ruben
    0.07
    Activations Density 0.021%

    No Known Activations