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. 111666
    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
    Resolved
    -0.08
    顿
    -0.07
    Phy
    -0.07
    Rel
    -0.07
     get
    -0.07
     పవ
    -0.07
    uniya
    -0.07
    /images
    -0.07
    クラ
    -0.07
    _phy
    -0.07
    POSITIVE LOGITS
     dozen
    0.10
     Damascus
    0.08
     şey
    0.08
    gebruik
    0.08
     crip
    0.08
    vollen
    0.08
    ವಾದ
    0.08
    ším
    0.07
     etwas
    0.07
    thing
    0.07
    Activations Density 0.115%

    No Known Activations