© 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. 19106
    Prev
    Next
    INDEX
    Explanations

    say "to" or "from"

    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
    'ha
    -0.09
    ள்
    -0.08
    ṇa
    -0.08
    'avez
    -0.08
     »
    -0.08
     рынок
    -0.07
     　 　
    -0.07
    CESS
    -0.07
     ॥
    -0.07
    ১৫
    -0.07
    POSITIVE LOGITS
    _to
    0.24
    To
    0.20
    _of
    0.19
    -to
    0.19
    -of
    0.18
    _from
    0.17
    _for
    0.17
    _by
    0.17
    Of
    0.16
    _with
    0.16
    Activations Density 0.020%

    No Known Activations