© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 47554
    Prev
    Next
    INDEX
    Explanations

    accusations

    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
    es
    -0.13
    ens
    -0.11
    escence
    -0.10
    ensation
    -0.09
     applicability
    -0.08
     allocation
    -0.08
    ével
    -0.08
    -f
    -0.08
    -key
    -0.08
     convergence
    -0.08
    POSITIVE LOGITS
    ijdt
    0.12
     dislikes
    0.11
    umbles
    0.10
    emplates
    0.10
    areth
    0.10
     complains
    0.10
     sheegay
    0.10
    ätzt
    0.10
     loves
    0.10
     vows
    0.10
    Activations Density 0.038%

    No Known Activations