© 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. 103035
    Prev
    Next
    INDEX
    Explanations

    1

    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
     שני
    -0.09
     Deux
    -0.08
     both
    -0.08
    елябин
    -0.08
     togg
    -0.08
     zweimal
    -0.08
    毎
    -0.08
     Beide
    -0.08
    toggle
    -0.08
    ере
    -0.08
    POSITIVE LOGITS
     hoặc
    0.10
     yleensä
    0.10
     기간
    0.09
     alebo
    0.09
     Duration
    0.09
     లేదా
    0.08
     अवधि
    0.08
     CAGR
    0.08
     IEC
    0.08
     prepaid
    0.08
    Activations Density 0.004%

    No Known Activations