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. 114007
    Prev
    Next
    INDEX
    Explanations

    coding special characters

    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
    ünü
    -0.08
     nurse
    -0.08
     allergic
    -0.08
     alf
    -0.08
    ingss
    -0.08
    /manage
    -0.08
     ಶಾಸ
    -0.07
     soldier
    -0.07
     intox
    -0.07
     ESA
    -0.07
    POSITIVE LOGITS
     notation
    0.10
    -pref
    0.09
     squared
    0.08
     propio
    0.07
    ператор
    0.07
     കൊണ്ട്
    0.07
     வைத்து
    0.07
     Brendan
    0.07
     denotes
    0.07
    Notation
    0.07
    Activations Density 0.020%

    No Known Activations