Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 47090
    Prev
    Next
    INDEX
    Explanations

    HIV

    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
     Schwarz
    -0.08
    和值
    -0.08
    柱
    -0.08
     legge
    -0.08
     اللغة
    -0.08
     blo
    -0.07
     franz
    -0.07
     escult
    -0.07
    铺
    -0.07
     diaphragm
    -0.07
    POSITIVE LOGITS
    /AIDS
    0.20
     HIV
    0.08
    AM
    0.08
     infection
    0.08
     globalization
    0.07
     globally
    0.07
    storm
    0.07
     Condom
    0.07
     Infection
    0.07
     infections
    0.07
    Activations Density 0.002%

    No Known Activations