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. 342
    Prev
    Next
    INDEX
    Explanations

    by

    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
    Frequently
    -0.08
    TAB
    -0.08
     TAB
    -0.08
    /ar
    -0.08
    、副
    -0.08
     असून
    -0.08
     axi
    -0.07
    답
    -0.07
     genu
    -0.07
    दार
    -0.07
    POSITIVE LOGITS
     mosquito
    0.10
     mosquitoes
    0.09
     Nazis
    0.08
     snakes
    0.08
     Gewalt
    0.08
    iej
    0.08
     bull
    0.08
     snake
    0.07
     someone
    0.07
     alguien
    0.07
    Activations Density 0.040%

    No Known Activations