© 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. 102761
    Prev
    Next
    INDEX
    Explanations

    NMR and isotopes

    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
     Mobil
    -0.10
     mobil
    -0.09
    Mobil
    -0.09
    riterien
    -0.09
     papill
    -0.09
    mobil
    -0.09
     Prosecut
    -0.09
     tuss
    -0.08
     peri
    -0.08
     bung
    -0.08
    POSITIVE LOGITS
     (^
    0.15
     ^
    0.15
    (^
    0.11
    ¹
    0.11
     isotope
    0.11
     ^^
    0.10
    ,^
    0.10
    ^(
    0.10
     MAS
    0.10
    /^
    0.10
    Activations Density 0.004%

    No Known Activations