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. 45831
    Prev
    Next
    INDEX
    Explanations

    cryptography

    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
     SWOT
    -0.10
     Playlist
    -0.10
     Movie
    -0.09
    _artist
    -0.09
    Airport
    -0.09
     Mariners
    -0.09
     Municipal
    -0.08
     BOM
    -0.08
    arto
    -0.08
     climat
    -0.08
    POSITIVE LOGITS
     proofs
    0.12
     prover
    0.12
     proving
    0.10
     computational
    0.10
     proved
    0.09
     prove
    0.09
     proof
    0.09
     démon
    0.08
    Proof
    0.08
     infe
    0.08
    Activations Density 0.002%

    No Known Activations