© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 18472
    Prev
    Next
    INDEX
    Explanations

    Memory allocation numbers

    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
     geloven
    -0.10
    "Our
    -0.10
    "A
    -0.09
    could
    -0.09
    "C
    -0.09
    "
    -0.09
     könnten
    -0.09
    "G
    -0.09
    "고
    -0.09
    "ח
    -0.09
    POSITIVE LOGITS
    _t
    0.35
    _T
    0.17
    _ts
    0.17
    _type
    0.14
    T
    0.14
    t
    0.13
    .t
    0.12
    -t
    0.12
    _k
    0.12
    _tt
    0.12
    Activations Density 0.002%

    No Known Activations