© 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. 97632
    Prev
    Next
    INDEX
    Explanations

    à

    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
     einzig
    -0.09
     aldus
    -0.08
     наконец
    -0.08
     àm
    -0.08
    을
    -0.08
     maakt
    -0.08
     siendo
    -0.08
    את
    -0.08
    なら
    -0.08
    に
    -0.07
    POSITIVE LOGITS
     partir
    0.21
     travers
    0.17
     proximité
    0.16
     partire
    0.15
     través
    0.15
     disposizione
    0.15
     propos
    0.15
     droite
    0.14
     volonté
    0.14
     respeito
    0.14
    Activations Density 0.007%

    No Known Activations