© 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. 11-RESID-POST-AA
    11. 70051
    Prev
    Next
    INDEX
    Explanations

    alignment in columnar format

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     episódios
    -0.08
    \Collection
    -0.08
     સર્જ
    -0.07
     props
    -0.07
     férias
    -0.07
    /N
    -0.07
     NFTs
    -0.07
     dynamics
    -0.07
     ELE
    -0.07
    _Injected
    -0.07
    POSITIVE LOGITS
    Align
    0.10
     alignment
    0.10
    aligned
    0.09
     hiz
    0.09
    -align
    0.09
     aligning
    0.09
     lì
    0.09
    align
    0.09
    .align
    0.09
     shifted
    0.09
    Activations Density 0.008%

    No Known Activations