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. 98009
    Prev
    Next
    INDEX
    Explanations

    tổng

    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
    ionic
    -0.09
    ions
    -0.08
     #
    -0.08
    ous
    -0.08
     neighbor
    -0.07
    uteurs
    -0.07
     replic
    -0.07
    uidor
    -0.07
     Dior
    -0.07
     Eingang
    -0.07
    POSITIVE LOGITS
    fassung
    0.14
    fass
    0.12
    führen
    0.11
    fasst
    0.10
    führung
    0.10
    fad
    0.10
    führt
    0.10
    fat
    0.10
    fatt
    0.10
    ்க்க
    0.09
    Activations Density 0.001%

    No Known Activations