© 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. 103154
    Prev
    Next
    INDEX
    Explanations

    Guiding light

    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
     configs
    -0.09
    izando
    -0.08
    �运
    -0.08
    izing
    -0.08
    izados
    -0.07
    izzato
    -0.07
     एवं
    -0.07
    ized
    -0.07
    ando
    -0.07
    ings
    -0.07
    POSITIVE LOGITS
     Einige
    0.11
     some
    0.10
    �
    0.10
    辰
    0.10
     several
    0.09
    迹
    0.09
     let's
    0.09
     Algunos
    0.09
     같습니다
    0.09
     the
    0.09
    Activations Density 0.008%

    No Known Activations