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. 54207
    Prev
    Next
    INDEX
    Explanations

    ,

    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
     Aunt
    -0.08
     Flexible
    -0.08
     recepción
    -0.08
     Rece
    -0.08
     imagen
    -0.08
     tossed
    -0.08
     fluctu
    -0.08
    认为
    -0.08
    _RECE
    -0.07
     evaluación
    -0.07
    POSITIVE LOGITS
     coragem
    0.09
     courage
    0.09
    bold
    0.09
     courageous
    0.09
    oin
    0.08
    winner
    0.08
     bold
    0.08
     libido
    0.08
     testosterone
    0.08
     assert
    0.08
    Activations Density 0.002%

    No Known Activations