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. 61094
    Prev
    Next
    INDEX
    Explanations

    |

    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
    cind
    -0.07
     Muitas
    -0.07
     tä
    -0.07
     contín
    -0.07
    illusion
    -0.07
     gewesen
    -0.07
     fatig
    -0.07
     he'd
    -0.07
    /un
    -0.07
    isierten
    -0.07
    POSITIVE LOGITS
    Gameplay
    0.09
    Main
    0.09
    _MAIN
    0.09
    arris
    0.09
     Main
    0.08
     Meadows
    0.08
    nz
    0.08
     γίνεται
    0.08
     Highlights
    0.08
     mainly
    0.08
    Activations Density 0.021%

    No Known Activations