© 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. 19-RESID-POST-AA
    11. 18733
    Prev
    Next
    INDEX
    Explanations

    in

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dizaines
    -0.10
     множество
    -0.09
    stantial
    -0.09
    -clear
    -0.09
     гораздо
    -0.09
    clear
    -0.09
    false
    -0.09
    !(
    -0.09
    much
    -0.09
    !</
    -0.09
    POSITIVE LOGITS
     relatie
    0.14
     Context
    0.14
     contexts
    0.13
     relation
    0.13
     contexto
    0.11
     relazione
    0.11
     context
    0.11
    	context
    0.11
     Kontext
    0.11
     Relation
    0.11
    Activations Density 0.041%

    No Known Activations