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. 44867
    Prev
    Next
    INDEX
    Explanations

    Number sequences

    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
     hinsichtlich
    -0.08
     воспри
    -0.08
     όσ
    -0.08
     perceived
    -0.08
     excessive
    -0.08
     गर्दा
    -0.08
     regarding
    -0.08
     cuanto
    -0.07
     perceb
    -0.07
     prone
    -0.07
    POSITIVE LOGITS
     explicitly
    0.08
    Reach
    0.08
    涛
    0.08
    Explicit
    0.07
    ્રણ
    0.07
    =headers
    0.07
     presentes
    0.07
     DIRECT
    0.07
    عين
    0.07
     ninu
    0.07
    Activations Density 0.043%

    No Known Activations