© 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. 78352
    Prev
    Next
    INDEX
    Explanations

    services

    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
     pistol
    -0.08
    Extend
    -0.08
     apartment
    -0.08
    Apartment
    -0.08
    \Common
    -0.08
     pancake
    -0.08
    Queue
    -0.08
     peptides
    -0.08
    xaa
    -0.08
     swimmers
    -0.07
    POSITIVE LOGITS
     assimil
    0.08
     laure
    0.07
    789
    0.07
     mely
    0.07
     digitales
    0.07
    ว่า
    0.07
     animated
    0.07
     ht
    0.07
    607
    0.07
    -license
    0.07
    Activations Density 0.004%

    No Known Activations