Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12167
    Prev
    Next
    INDEX
    Explanations

    identity

    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
    Presenter
    -0.08
    gran
    -0.08
     Stephen
    -0.08
     reh
    -0.07
     indications
    -0.07
    entr
    -0.07
     uplift
    -0.07
     சந்த
    -0.07
    Cy
    -0.07
     spear
    -0.07
    POSITIVE LOGITS
    Facts
    0.09
    成立
    0.08
    ్స్
    0.08
     lè
    0.07
    公式
    0.07
     Silk
    0.07
    背
    0.07
    .Acc
    0.07
    一下
    0.07
     Alfred
    0.07
    Activations Density 0.005%

    No Known Activations