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. 30643
    Prev
    Next
    INDEX
    Explanations

    hazardous materials

    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
     Νο
    -0.08
     লাগে
    -0.08
     nause
    -0.08
     Dungeon
    -0.08
    近日
    -0.08
    crypto
    -0.07
     Hang
    -0.07
    capacity
    -0.07
    ících
    -0.07
     Sever
    -0.07
    POSITIVE LOGITS
     وتص
    0.09
     residencial
    0.09
     residential
    0.09
    ्वर
    0.08
    住宅
    0.08
     ruch
    0.08
     SSA
    0.08
    ОМ
    0.08
    DAR
    0.07
    Residential
    0.07
    Activations Density 0.002%

    No Known Activations