© 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. 50602
    Prev
    Next
    INDEX
    Explanations

    encompassing and cancelling

    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
    ização
    -0.11
    ización
    -0.11
    ization
    -0.10
     Reception
    -0.10
    iques
    -0.10
    izing
    -0.10
    icity
    -0.09
    ское
    -0.09
    ing
    -0.09
    ский
    -0.09
    POSITIVE LOGITS
    assed
    0.13
    assment
    0.12
    त्ति
    0.11
    żli
    0.11
    ursal
    0.11
    actical
    0.10
    mbles
    0.10
    aviors
    0.10
    uscht
    0.10
    illors
    0.09
    Activations Density 0.076%

    No Known Activations