© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30899
    Prev
    Next
    INDEX
    Explanations

    Staphylococcus aureus bacteria

    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
     pher
    -0.08
     sensual
    -0.08
    eneration
    -0.08
     pari
    -0.07
     Kail
    -0.07
     cu
    -0.07
    _href
    -0.07
     execution
    -0.07
     censor
    -0.07
     dhim
    -0.07
    POSITIVE LOGITS
    0.09
    ást
    0.09
     inoxidable
    0.08
    Enterprise
    0.08
    ോയ
    0.08
     aure
    0.08
    nota
    0.08
     whole
    0.08
     norsk
    0.07
    این
    0.07
    Activations Density 0.004%

    No Known Activations