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. 76387
    Prev
    Next
    INDEX
    Explanations

    on

    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
     लेखक
    -0.08
     htmlentities
    -0.08
     पुन
    -0.08
     తయ
    -0.08
     során
    -0.08
     Winners
    -0.08
    _include
    -0.08
     SPDX
    -0.07
     એની
    -0.07
     അപ
    -0.07
    POSITIVE LOGITS
    住
    0.09
    夫
    0.08
     cockpit
    0.08
     balcony
    0.08
    户
    0.08
    ocked
    0.08
     east
    0.08
     flushed
    0.08
     stationed
    0.08
    Outgoing
    0.08
    Activations Density 0.008%

    No Known Activations