Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 12213
    Prev
    Next
    INDEX
    Explanations

    quantity math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    अर
    -0.08
    ्न
    -0.08
    aktu
    -0.08
    emand
    -0.07
     Engage
    -0.07
    afile
    -0.07
    aza
    -0.07
     manj
    -0.07
     API
    -0.07
    .qt
    -0.07
    POSITIVE LOGITS
     rehetra
    0.11
     hinweg
    0.10
    238
    0.09
     gape
    0.08
     collectively
    0.08
     உர
    0.08
     tykk
    0.08
     totaled
    0.08
     führte
    0.08
     toplam
    0.08
    Activations Density 0.074%

    No Known Activations