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. 300
    Prev
    Next
    INDEX
    Explanations

    _x

    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
     حاضر
    -0.09
     PRESENT
    -0.09
     Marianne
    -0.08
     Oll
    -0.08
     nomin
    -0.08
     Brooklyn
    -0.08
     blackberry
    -0.08
     במ
    -0.07
     Greene
    -0.07
     présent
    -0.07
    POSITIVE LOGITS
    Proc
    0.08
     uku
    0.08
     catered
    0.08
    ТП
    0.07
    Д
    0.07
     streamed
    0.07
    wys
    0.07
    613
    0.07
    Well
    0.07
     uchel
    0.07
    Activations Density 0.001%

    No Known Activations