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. 97996
    Prev
    Next
    INDEX
    Explanations

    Ancient city-states

    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
     arc
    -0.09
    アウト
    -0.09
    _arc
    -0.08
    Ctr
    -0.07
     peek
    -0.07
    บาท
    -0.07
    Positions
    -0.07
    ภาพ
    -0.07
    Washington
    -0.07
    พื้นที่
    -0.07
    POSITIVE LOGITS
     ch
    0.10
     Mel
    0.08
     Ch
    0.08
     sopr
    0.08
     Mun
    0.08
     sangu
    0.08
     kuti
    0.08
     Guardia
    0.08
    auri
    0.08
     Euchar
    0.08
    Activations Density 0.001%

    No Known Activations