© 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. 54838
    Prev
    Next
    INDEX
    Explanations

    Mortgage-backed securities

    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
     unin
    -0.08
     oxid
    -0.08
     �
    -0.08
     不
    -0.07
     misleading
    -0.07
     specific
    -0.07
     inflammatory
    -0.07
     vision
    -0.07
    !!
    -0.07
     biotech
    -0.07
    POSITIVE LOGITS
     США
    0.09
    ，全国
    0.08
     abandonar
    0.08
     전국
    0.08
     अपे
    0.08
     Files
    0.08
     Expected
    0.08
     түс
    0.08
     buwan
    0.08
     téléphone
    0.08
    Activations Density 0.003%

    No Known Activations