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. 9209
    Prev
    Next
    INDEX
    Explanations

    PyTorch model saving/loading

    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
     rhy
    -0.08
     sufferers
    -0.08
     aşk
    -0.08
    etna
    -0.08
    horia
    -0.08
    "What
    -0.08
    互动
    -0.08
     engaging
    -0.08
     dramat
    -0.08
     plead
    -0.08
    POSITIVE LOGITS
     checkpoint
    0.13
    Checkpoint
    0.12
    _checkpoint
    0.11
     checkpoints
    0.10
    checkpoint
    0.10
     deserialize
    0.09
     hashes
    0.09
     pretrained
    0.08
     sync
    0.08
     thaw
    0.08
    Activations Density 0.004%

    No Known Activations