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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44773
    Prev
    Next
    INDEX
    Explanations

    References

    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
    ্ট
    -0.07
    .adapters
    -0.07
    prung
    -0.07
     tracks
    -0.07
    陪
    -0.07
    রের
    -0.07
     出
    -0.07
    YPES
    -0.07
    پر
    -0.07
     sk
    -0.07
    POSITIVE LOGITS
    alliative
    0.08
    flate
    0.08
     إليه
    0.08
    ves
    0.08
     prosperous
    0.08
    urrencies
    0.08
    ancies
    0.08
    atieven
    0.08
     Weed
    0.07
     Monetary
    0.07
    Activations Density 0.000%

    No Known Activations