© 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. 102960
    Prev
    Next
    INDEX
    Explanations

    marketing launch goals

    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
    sometimes
    -0.12
    حيان
    -0.12
     parfois
    -0.11
     moltes
    -0.11
     manchmal
    -0.11
     sageli
    -0.11
    ередко
    -0.11
    often
    -0.11
     veces
    -0.10
     übrigens
    -0.10
    POSITIVE LOGITS
     möglichst
    0.13
    ，提高
    0.13
    ，实现
    0.11
    ’ici
    0.10
     sustainably
    0.10
     максимально
    0.10
     sustainable
    0.10
     mindestens
    0.10
     بتوان
    0.10
    全面
    0.10
    Activations Density 0.111%

    No Known Activations