© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 18009
    Prev
    Next
    INDEX
    Explanations

    parameters

    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
    Negative Logits
    लाई
    -0.09
     presidential
    -0.08
     От
    -0.08
     �
    -0.07
     Presidential
    -0.07
    $list
    -0.07
    \xe
    -0.07
    -0.07
    =>"
    -0.07
    ionista
    -0.07
    POSITIVE LOGITS
     parameters
    0.25
    Parameters
    0.22
     Parameters
    0.21
    _parameters
    0.20
    parameters
    0.20
    (parameters
    0.19
     PARAMETERS
    0.18
    	parameters
    0.17
     parámetros
    0.16
    _PARAMETERS
    0.16
    Activations Density 0.060%
    No Known Activations