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. 7-RESID-POST-AA
    6. 131051
    Prev
    Next
    INDEX
    Explanations

    M

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Parte
    -0.08
     forensic
    -0.08
     largos
    -0.07
    ceived
    -0.07
     LIB
    -0.07
    istra
    -0.07
    obt
    -0.07
     Umfang
    -0.07
     Agua
    -0.07
     profund
    -0.07
    POSITIVE LOGITS
    .depart
    0.09
     gyro
    0.09
    étique
    0.08
     governor
    0.08
     rapides
    0.08
    ощ
    0.08
    _depart
    0.08
     सिद्ध
    0.08
     בנ
    0.08
     gambling
    0.08
    Activations Density 0.002%

    No Known Activations