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. 9159
    Prev
    Next
    INDEX
    Explanations

    body

    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
     président
    -0.08
     matter
    -0.08
     MAT
    -0.08
     constraints
    -0.07
     smaller
    -0.07
    चान
    -0.07
     poche
    -0.07
    pee
    -0.07
     size
    -0.07
     CCD
    -0.07
    POSITIVE LOGITS
     aman
    0.09
     TYPES
    0.09
     Aman
    0.09
     Maxim
    0.08
     myster
    0.08
    ulers
    0.08
     വീണ്ടും
    0.08
    -Control
    0.08
     bizarre
    0.08
     Solaris
    0.08
    Activations Density 0.001%

    No Known Activations