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. 45115
    Prev
    Next
    INDEX
    Explanations

    spirituality, alignment, consciousness

    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
    zyma
    -0.08
     user
    -0.08
    agner
    -0.07
     Oreo
    -0.07
     pizza
    -0.07
    ANDOM
    -0.07
     пользователь
    -0.07
     المستخدم
    -0.07
    成绩
    -0.07
    _ARGS
    -0.07
    POSITIVE LOGITS
     mindfulness
    0.11
     Reiki
    0.11
     tantra
    0.10
     herm
    0.10
     spiritually
    0.10
     Chakra
    0.10
     Spiritual
    0.10
     Herm
    0.09
     beautifully
    0.09
     profundo
    0.09
    Activations Density 0.128%

    No Known Activations