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

    Neuronpedia

    Jacobian LensNEW
    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. 11-RESID-POST-AA
    11. 69047
    Prev
    Next
    INDEX
    Explanations

    age

    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
     equivalents
    -0.08
    parallel
    -0.08
     parallel
    -0.08
     simultaneous
    -0.08
     vibration
    -0.07
    /sl
    -0.07
    /rss
    -0.07
     interrup
    -0.07
    ’un
    -0.07
    Rl
    -0.07
    POSITIVE LOGITS
     यांनी
    0.09
    舞
    0.08
     ஆகிய
    0.08
    Miles
    0.08
     livelihoods
    0.08
    Patrick
    0.08
    Pretty
    0.08
    Apellido
    0.07
    描述
    0.07
    _fields
    0.07
    Activations Density 0.018%

    No Known Activations