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. 77573
    Prev
    Next
    INDEX
    Explanations

    pointer

    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
     wastewater
    -0.09
     Temple
    -0.08
     borderline
    -0.08
     casualty
    -0.08
     explosives
    -0.08
    IRI
    -0.08
     thoroughly
    -0.08
    kẹ
    -0.08
    дим
    -0.07
     trolley
    -0.07
    POSITIVE LOGITS
     på
    0.08
     ptr
    0.08
     inj
    0.08
    🏼
    0.07
    mera
    0.07
     Mog
    0.07
    joe
    0.07
     Richard
    0.07
     Mom
    0.07
     На
    0.07
    Activations Density 0.003%

    No Known Activations