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. 130793
    Prev
    Next
    INDEX
    Explanations

    accr

    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
     mourning
    -0.09
     embarking
    -0.08
    zwa
    -0.08
    verkehr
    -0.08
    ാറ്റ
    -0.08
    اتی
    -0.08
    presa
    -0.08
    ાકી
    -0.08
    ાવવામાં
    -0.08
     Verpack
    -0.07
    POSITIVE LOGITS
    ual
    0.17
    UAL
    0.11
    itif
    0.09
    ually
    0.09
    ues
    0.09
    ades
    0.09
    uales
    0.09
    ुअ
    0.09
    ualitas
    0.09
    ylon
    0.09
    Activations Density 0.001%

    No Known Activations