© 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. 23-RESID-POST-AA
    11. 51820
    Prev
    Next
    INDEX
    Explanations

    =

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Magna
    -0.08
     Disposable
    -0.08
     счита
    -0.08
     yer
    -0.07
     reconocido
    -0.07
     callable
    -0.07
     �
    -0.07
     sobra
    -0.07
    _Not
    -0.07
     nö
    -0.07
    POSITIVE LOGITS
    rosi
    0.07
    ент
    0.07
     internetu
    0.07
    ostr
    0.07
     tier
    0.07
    алды
    0.07
     accession
    0.07
     uwagę
    0.07
    →
    0.07
    аман
    0.07
    Activations Density 0.000%

    No Known Activations