Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 19541
    Prev
    Next
    INDEX
    Explanations

    Focus

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vô
    -0.08
    בוע
    -0.07
    raz
    -0.07
    лег
    -0.07
     sliced
    -0.07
    usu
    -0.07
    amo
    -0.07
     stamped
    -0.07
    เว็บ
    -0.07
     ipsum
    -0.07
    POSITIVE LOGITS
    =my
    0.08
    0.08
     Stich
    0.08
     스타
    0.07
     NOR
    0.07
    онар
    0.07
    (Intent
    0.07
     �
    0.07
     The
    0.07
    债
    0.07
    Activations Density 1.258%

    No Known Activations