© 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. 44590
    Prev
    Next
    INDEX
    Explanations

    Cl

    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
     Fach
    -0.07
    алах
    -0.07
    _argument
    -0.07
     Care
    -0.07
    Argument
    -0.07
    飞
    -0.07
     threatened
    -0.07
     argument
    -0.07
    佛
    -0.07
    argument
    -0.07
    POSITIVE LOGITS
    dvd
    0.08
     hydrochlor
    0.08
     implic
    0.08
     раствор
    0.08
    ieuse
    0.08
    istoj
    0.08
     frustr
    0.08
    遣
    0.08
    rase
    0.07
     midi
    0.07
    Activations Density 0.004%

    No Known Activations