© 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. 11-RESID-POST-AA
    11. 54670
    Prev
    Next
    INDEX
    Explanations

    "for" in English/Spanish

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    じ
    -0.08
     Mondays
    -0.08
    ographer
    -0.08
     Scalars
    -0.08
    icks
    -0.08
     نت
    -0.07
    ick
    -0.07
     rocking
    -0.07
     Monday
    -0.07
    icklabels
    -0.07
    POSITIVE LOGITS
     gồm
    0.10
     구성
    0.09
     constitué
    0.09
     terdiri
    0.09
     består
    0.08
     composée
    0.08
    ประก
    0.08
     composta
    0.08
     igualmente
    0.07
     pax
    0.07
    Activations Density 0.063%

    No Known Activations