© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 103305
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ailability
    -0.08
    (record
    -0.08
    Getter
    -0.08
    Deserializer
    -0.07
    Consistency
    -0.07
    Record
    -0.07
    Accumulator
    -0.07
    Aggregator
    -0.07
     aggregator
    -0.07
    ונט
    -0.07
    POSITIVE LOGITS
     остальных
    0.09
     others
    0.09
     jeweiligen
    0.09
    وال
    0.08
     Marques
    0.08
     ones
    0.08
     個
    0.08
     Mf
    0.07
    bamos
    0.07
     individuellen
    0.07
    Activations Density 0.004%

    No Known Activations