© 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. 103007
    Prev
    Next
    INDEX
    Explanations

    temperature

    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
     exist
    -0.09
     دارای
    -0.08
     имеют
    -0.08
     leey
    -0.08
     are
    -0.08
    -0.08
     istnie
    -0.08
     существуют
    -0.08
     manana
    -0.08
     possuem
    -0.08
    POSITIVE LOGITS
     reaches
    0.23
    达到
    0.19
     atteindre
    0.18
     mencapai
    0.17
     reaching
    0.17
     atingir
    0.17
     reach
    0.16
     পৌঁ
    0.16
     atteint
    0.16
     raggi
    0.16
    Activations Density 0.019%

    No Known Activations