© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 102934
    Prev
    Next
    INDEX
    Explanations

    previously

    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
    езульт
    -0.08
    ánchez
    -0.08
    /[
    -0.08
    онят
    -0.07
     videre
    -0.07
    early
    -0.07
    ([
    -0.07
     early
    -0.07
    аран
    -0.07
    ņas
    -0.07
    POSITIVE LOGITS
     previously
    0.27
     auparavant
    0.26
     zuvor
    0.25
     sebelumnya
    0.24
     Previously
    0.23
    之前
    0.23
     anteriormente
    0.23
    Previously
    0.22
     અગાઉ
    0.22
     ранее
    0.21
    Activations Density 0.041%

    No Known Activations