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. 106125
    Prev
    Next
    INDEX
    Explanations

    guidance

    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
    φαν
    -0.09
     ban
    -0.08
    ங
    -0.08
    ഞ്ഞ
    -0.08
     rumor
    -0.08
     amus
    -0.08
     scare
    -0.08
    WN
    -0.08
     juiste
    -0.08
     rumores
    -0.07
    POSITIVE LOGITS
    指导
    0.13
     guidance
    0.12
     begeleiding
    0.12
     Guidance
    0.11
     mentorship
    0.11
     supervision
    0.11
    导师
    0.11
     mentors
    0.11
     Mentor
    0.10
     mentor
    0.10
    Activations Density 0.018%

    No Known Activations