Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 98039
    Prev
    Next
    INDEX
    Explanations

    |

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     véhic
    -0.08
     kontro
    -0.08
     ogranic
    -0.08
     serrurerie
    -0.08
    äder
    -0.08
     механ
    -0.08
     controversies
    -0.08
     dambe
    -0.07
     oj
    -0.07
     конт
    -0.07
    POSITIVE LOGITS
     taux
    0.16
     hausse
    0.14
     nombre
    0.13
    Nombre
    0.12
     Nombre
    0.12
    augmentation
    0.12
     seuil
    0.12
    nombre
    0.12
     CAGR
    0.12
    ratio
    0.12
    Activations Density 0.040%

    No Known Activations