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. 97051
    Prev
    Next
    INDEX
    Explanations

    Ke

    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
    quen
    -0.09
    વાર
    -0.08
    qu
    -0.07
    વું
    -0.07
     оказ
    -0.07
     concerto
    -0.07
    (...
    -0.07
     Attachment
    -0.07
    :%
    -0.07
     зам
    -0.07
    POSITIVE LOGITS
     большие
    0.09
     peces
    0.09
     big
    0.09
    ěst
    0.08
     terres
    0.08
    ilerin
    0.08
    әы
    0.08
     პირდაპირ
    0.08
     अक्ष
    0.08
     felices
    0.08
    Activations Density 0.000%

    No Known Activations