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. 55142
    Prev
    Next
    INDEX
    Explanations

    Dash

    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
    vival
    -0.09
     infusion
    -0.08
     asunto
    -0.08
     intentional
    -0.08
     compounded
    -0.08
     infused
    -0.08
    ullah
    -0.08
     artificially
    -0.08
    بود
    -0.08
     pinag
    -0.08
    POSITIVE LOGITS
    (props
    0.10
     Vertical
    0.09
     Props
    0.09
    Dropdown
    0.09
     Dialog
    0.09
     Displays
    0.09
    .Footer
    0.09
     Horizontal
    0.09
     Dialogue
    0.09
     Wrapper
    0.08
    Activations Density 0.008%

    No Known Activations