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. 45137
    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
     interests
    -0.08
    dib
    -0.07
    (relative
    -0.07
     représentant
    -0.07
    Kaj
    -0.07
    gey
    -0.07
     ppm
    -0.07
     MATCH
    -0.07
     bestseller
    -0.07
    Above
    -0.07
    POSITIVE LOGITS
     приступ
    0.09
    )을
    0.08
     метав
    0.08
    .Invalid
    0.07
    тива
    0.07
     procuram
    0.07
    0.07
    erral
    0.07
     desesper
    0.07
    Repair
    0.07
    Activations Density 0.001%

    No Known Activations