© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 103636
    Prev
    Next
    INDEX
    Explanations

    say "dimension"

    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
     Silence
    -0.09
     Gerr
    -0.09
     последствия
    -0.09
    ేషన్
    -0.09
    _dispatch
    -0.09
     apuesta
    -0.09
     Assad
    -0.08
     Erwart
    -0.08
     reakc
    -0.08
     allegiance
    -0.08
    POSITIVE LOGITS
     by
    0.19
     width
    0.17
    ×
    0.15
    .width
    0.15
    (width
    0.15
    -by
    0.15
     wide
    0.14
    By
    0.14
    width
    0.14
    -width
    0.13
    Activations Density 0.012%

    No Known Activations