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. 78556
    Prev
    Next
    INDEX
    Explanations

    timeline

    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
     express
    -0.09
    Express
    -0.08
     expressing
    -0.08
    express
    -0.08
    fd
    -0.08
     expressive
    -0.08
     uttry
    -0.07
     expr
    -0.07
     Express
    -0.07
    fortawesome
    -0.07
    POSITIVE LOGITS
     alteration
    0.10
     alterations
    0.09
     alters
    0.09
     수정
    0.09
     стран
    0.09
     आब
    0.08
     Incorrect
    0.08
     conséquences
    0.08
     viajeros
    0.08
     alterar
    0.08
    Activations Density 0.013%

    No Known Activations