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. 30724
    Prev
    Next
    INDEX
    Explanations

    positively

    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
    Deviation
    -0.09
    Mental
    -0.09
    Ou
    -0.09
     exame
    -0.08
    Ц
    -0.08
    Denne
    -0.08
    rea
    -0.08
     examinations
    -0.07
    Produced
    -0.07
     reproduct
    -0.07
    POSITIVE LOGITS
    哪里
    0.08
     identities
    0.08
     glowing
    0.08
     thrilled
    0.08
    邪
    0.08
    epte
    0.08
     معلوم
    0.08
     vortex
    0.07
    ENTITY
    0.07
     અજ
    0.07
    Activations Density 0.004%

    No Known Activations