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. 60708
    Prev
    Next
    INDEX
    Explanations

    philosophy and ethics

    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
     Mahal
    -0.08
     cookies
    -0.08
     박
    -0.08
    �
    -0.08
     플
    -0.08
    };↵↵//
    -0.08
     pesada
    -0.07
    ్
    -0.07
     seasoned
    -0.07
     silk
    -0.07
    POSITIVE LOGITS
     causal
    0.09
     normative
    0.09
     Judgment
    0.09
    性感
    0.09
     immoral
    0.09
     judgments
    0.09
    ordinal
    0.09
     morally
    0.08
    latent
    0.08
     harms
    0.08
    Activations Density 0.046%

    No Known Activations