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. 104086
    Prev
    Next
    INDEX
    Explanations

    arrow keys

    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
    Fernando
    -0.08
    Sampling
    -0.08
     apresentam
    -0.08
    Fixture
    -0.08
    စ္
    -0.08
     franceses
    -0.08
    _INSTANCE
    -0.08
    Occurrence
    -0.08
    Bless
    -0.07
    datatable
    -0.07
    POSITIVE LOGITS
     directions
    0.10
     Directions
    0.09
     afuera
    0.09
    Directions
    0.08
     söö
    0.08
     الأرب
    0.08
     밖
    0.07
    ministr
    0.07
     energies
    0.07
     сырт
    0.07
    Activations Density 0.003%

    No Known Activations