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. 42869
    Prev
    Next
    INDEX
    Explanations

    single-digit numbers

    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
     crunchy
    -0.08
     crunch
    -0.07
    أما
    -0.07
     Glaub
    -0.07
     Crunch
    -0.07
    While
    -0.07
     varying
    -0.07
     �
    -0.07
     substantive
    -0.07
    تے
    -0.07
    POSITIVE LOGITS
    024
    0.08
     күч
    0.08
     болсо
    0.08
     бір
    0.08
     prostitute
    0.08
     eeg
    0.08
     Direction
    0.08
    agnitude
    0.08
    Direction
    0.07
     ойл
    0.07
    Activations Density 0.022%

    No Known Activations