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. 98776
    Prev
    Next
    INDEX
    Explanations

    trolley problem

    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
     tendência
    -0.09
    ्तर
    -0.09
     anchors
    -0.08
     RVA
    -0.08
     fark
    -0.08
     Marken
    -0.08
    गार
    -0.08
     Persönlichkeit
    -0.08
    nvarchar
    -0.07
     Weis
    -0.07
    POSITIVE LOGITS
     altru
    0.10
    救
    0.10
     спас
    0.09
     pac
    0.09
     ambulance
    0.09
     হত্যা
    0.09
     salvar
    0.09
     sauver
    0.09
     compassion
    0.09
     atrocities
    0.09
    Activations Density 0.046%

    No Known Activations