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. 58507
    Prev
    Next
    INDEX
    Explanations

    unconditional

    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
     dll
    -0.08
     Eco
    -0.08
     sie
    -0.08
    Ice
    -0.08
     charcoal
    -0.08
    Stamp
    -0.07
     Williamson
    -0.07
     freezes
    -0.07
     آن
    -0.07
     Credit
    -0.07
    POSITIVE LOGITS
    verages
    0.07
    )p
    0.07
    Broad
    0.07
     climate
    0.07
     averaging
    0.07
    认为
    0.07
     तौर
    0.07
     réflex
    0.07
     Felt
    0.07
    हुँ
    0.07
    Activations Density 0.001%

    No Known Activations