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. 58297
    Prev
    Next
    INDEX
    Explanations

    Connecting devices to a TV

    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
    .metadata
    -0.09
    (metadata
    -0.08
    플
    -0.08
     Fug
    -0.07
    wagon
    -0.07
    $file
    -0.07
    firm
    -0.07
     gossip
    -0.07
    _Metadata
    -0.07
    jän
    -0.07
    POSITIVE LOGITS
     rud
    0.09
     output
    0.08
     renders
    0.08
    itionally
    0.08
     OUTPUT
    0.08
    output
    0.08
     подключ
    0.08
     uyg
    0.08
     improperly
    0.08
     коллед
    0.08
    Activations Density 0.010%

    No Known Activations