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. 90162
    Prev
    Next
    INDEX
    Explanations

    text generation

    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
     __________
    -0.09
    Donation
    -0.07
    ("/:
    -0.07
    _SWAP
    -0.07
     любовь
    -0.07
    ربي
    -0.07
     multiplayer
    -0.07
     experimentally
    -0.07
    +"]
    -0.07
    .SQLException
    -0.07
    POSITIVE LOGITS
     complying
    0.10
     comply
    0.10
     confidentiality
    0.09
     compliant
    0.09
     forbid
    0.09
     disguised
    0.09
    -only
    0.08
     prohibited
    0.08
     prohibits
    0.08
     forb
    0.08
    Activations Density 0.031%

    No Known Activations