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. 45365
    Prev
    Next
    INDEX
    Explanations

    The number one

    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
     optimale
    -0.08
     aka
    -0.08
     denied
    -0.08
    ું
    -0.08
    -0.07
     Meetup
    -0.07
     hvilket
    -0.07
    �
    -0.07
     agradable
    -0.07
     એ
    -0.07
    POSITIVE LOGITS
    constraints
    0.08
     לכך
    0.08
     ↵	↵
    0.08
    ýs
    0.08
    Equation
    0.08
     conceive
    0.08
    physics
    0.08
     decorr
    0.08
    fieldset
    0.08
     täysin
    0.08
    Activations Density 0.013%

    No Known Activations