© 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. 11-RESID-POST-AA
    11. 68646
    Prev
    Next
    INDEX
    Explanations

    transport

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Maths
    -0.08
     mathematics
    -0.08
    (Debug
    -0.08
    =s
    -0.08
    (do
    -0.07
    =start
    -0.07
    -0.07
     catal
    -0.07
    anta
    -0.07
     catalytic
    -0.07
    POSITIVE LOGITS
    reiche
    0.09
     beden
    0.08
     hidrat
    0.08
    ح
    0.08
    زام
    0.08
    حول
    0.08
     Hod
    0.08
     betrieben
    0.08
     volley
    0.08
    gegeben
    0.08
    Activations Density 0.001%
    No Known Activations