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. 58494
    Prev
    Next
    INDEX
    Explanations

    migration

    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
     reinigen
    -0.08
     高频
    -0.08
     Zugriff
    -0.08
    kses
    -0.08
    _TRIGGER
    -0.07
    ileged
    -0.07
    .access
    -0.07
    .urlopen
    -0.07
     Exercise
    -0.07
     hals
    -0.07
    POSITIVE LOGITS
     приез
    0.15
     reloc
    0.13
     emigr
    0.13
     relocating
    0.13
     migrant
    0.13
     migrants
    0.13
     relocation
    0.12
    迁
    0.12
     immigr
    0.12
     verhuis
    0.12
    Activations Density 0.014%

    No Known Activations