© 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. 48815
    Prev
    Next
    INDEX
    Explanations

    alias

    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
     Incent
    -0.08
     secluded
    -0.08
     indifer
    -0.08
     Circ
    -0.08
     Prom
    -0.07
     Sedan
    -0.07
     Fundo
    -0.07
    hdl
    -0.07
     World
    -0.07
     Cv
    -0.07
    POSITIVE LOGITS
     alias
    0.21
     artifacts
    0.20
    Artifacts
    0.19
     artifact
    0.18
    alias
    0.18
    _alias
    0.17
    .alias
    0.16
    _ALIAS
    0.16
    Alias
    0.16
    Ali
    0.16
    Activations Density 0.011%

    No Known Activations