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. 48353
    Prev
    Next
    INDEX
    Explanations

    electroly

    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
    Browse
    -0.08
    _ALIGNMENT
    -0.08
    ################################################################################
    -0.08
    .Gui
    -0.08
    ################################
    -0.08
    Mind
    -0.07
     Diseases
    -0.07
    _LOC
    -0.07
    晋
    -0.07
    进去
    -0.07
    POSITIVE LOGITS
     Affordable
    0.09
     affordable
    0.09
     cheaper
    0.08
     human
    0.08
    Affordable
    0.08
     mejores
    0.08
     günst
    0.07
     günstig
    0.07
     Sonnen
    0.07
     lyk
    0.07
    Activations Density 0.002%

    No Known Activations