Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 58813
    Prev
    Next
    INDEX
    Explanations

    ’s

    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
    vedor
    -0.10
     områder
    -0.09
    konto
    -0.08
    sei
    -0.08
     שכ
    -0.08
    Prescription
    -0.08
     Вер
    -0.08
    stillinger
    -0.08
     sebel
    -0.08
     Verse
    -0.08
    POSITIVE LOGITS
     conferences
    0.19
     конферен
    0.17
     மாந
    0.16
     festival
    0.16
     conference
    0.16
     Conferences
    0.16
     festivals
    0.15
     परिषद
    0.15
     مؤتمر
    0.15
     सम्मेलन
    0.15
    Activations Density 0.260%

    No Known Activations