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. 131040
    Prev
    Next
    INDEX
    Explanations

    quadr

    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
    INIT
    -0.08
    ಿನ್
    -0.08
     Latino
    -0.08
    נטים
    -0.08
    lob
    -0.08
     Lump
    -0.08
    LO
    -0.08
     perth
    -0.08
     criticize
    -0.08
     كلام
    -0.07
    POSITIVE LOGITS
    baar
    0.08
    ifad
    0.07
     Fra
    0.07
     rooted
    0.07
     yt
    0.07
     assegurar
    0.07
     présenter
    0.07
     default
    0.07
     eur
    0.07
    ửa
    0.07
    Activations Density 0.002%

    No Known Activations