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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RESID-POST-AA
    6. 54133
    Prev
    Next
    INDEX
    Explanations

    vehicle passengers

    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
     conditioning
    -0.07
     raz
    -0.07
     Conditioning
    -0.07
    ikon
    -0.07
     chall
    -0.07
     subse
    -0.07
     إ
    -0.07
     barren
    -0.07
    enta
    -0.07
    ín
    -0.07
    POSITIVE LOGITS
     occupants
    0.10
     सीट
    0.09
    voerder
    0.09
     бірге
    0.09
     amused
    0.08
     coupe
    0.08
    Passenger
    0.08
     acompanhante
    0.08
    载
    0.08
    агог
    0.08
    Activations Density 0.025%

    No Known Activations