© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 1325
    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_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     approx
    -0.10
     kick
    -0.08
    =>
    -0.08
     RR
    -0.08
     karo
    -0.08
     kicks
    -0.08
    isable
    -0.08
     KB
    -0.07
     chek
    -0.07
     RF
    -0.07
    POSITIVE LOGITS
     이러한
    0.08
     abal
    0.08
     Bishop
    0.08
     understated
    0.08
     essentiels
    0.08
     UNT
    0.08
     여러분
    0.08
     rightly
    0.08
    UPDATED
    0.08
     неж
    0.08
    Activations Density 0.111%

    No Known Activations