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. 3-RESID-POST-AA
    6. 2137
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
     datas
    -0.10
    Mig
    -0.08
     Syr
    -0.07
     место
    -0.07
     Eg
    -0.07
     Voc
    -0.07
    �
    -0.07
    mande
    -0.07
     manner
    -0.07
     Mig
    -0.07
    POSITIVE LOGITS
    (二
    0.09
     pem
    0.08
     unlucky
    0.08
     WHITE
    0.07
     cargos
    0.07
     포
    0.07
     IMAGE
    0.07
    häuser
    0.07
     acon
    0.07
     сен
    0.07
    Activations Density 0.103%

    No Known Activations