© 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. 79163
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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
    ovanja
    -0.08
     Kā
    -0.08
    tg
    -0.08
     tranquilidad
    -0.07
    �
    -0.07
    itra
    -0.07
    anga
    -0.07
     Verbrauch
    -0.07
    非常
    -0.07
    Loan
    -0.07
    POSITIVE LOGITS
     Increasing
    0.09
    Increasing
    0.08
     istr
    0.08
     ingred
    0.08
     increasing
    0.08
    (sentence
    0.08
     beef
    0.08
     doos
    0.08
     creciente
    0.07
     anf
    0.07
    Activations Density 0.028%

    No Known Activations