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. 424
    Prev
    Next
    INDEX
    Explanations

    perpendicular

    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
     cyfr
    -0.09
     autograph
    -0.09
     билет
    -0.09
     ingestion
    -0.09
     सेवन
    -0.09
     mailed
    -0.08
    จำนวน
    -0.08
     incomes
    -0.08
     герой
    -0.08
     literacy
    -0.08
    POSITIVE LOGITS
    _direction
    0.08
    _documents
    0.08
    _depth
    0.08
     regl
    0.08
    idable
    0.08
    mmm
    0.07
     geological
    0.07
    Normals
    0.07
    upl
    0.07
     depth
    0.07
    Activations Density 0.024%

    No Known Activations