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. 58936
    Prev
    Next
    INDEX
    Explanations

    each

    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
     Sut
    -0.09
     Render
    -0.08
    MAX
    -0.08
     dovoljno
    -0.07
    RESH
    -0.07
     Vid
    -0.07
    Matchers
    -0.07
     Maestro
    -0.07
     Tra
    -0.07
     Mint
    -0.07
    POSITIVE LOGITS
     değil
    0.08
     یو
    0.08
    aneously
    0.07
     pe
    0.07
    pe
    0.07
    ,然后
    0.07
    758
    0.07
    arily
    0.07
     Lips
    0.07
    ообраз
    0.07
    Activations Density 0.018%

    No Known Activations