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. 119303
    Prev
    Next
    INDEX
    Explanations

    hiking

    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
     crystal
    -0.08
     releg
    -0.08
    -commerce
    -0.08
    iferay
    -0.08
    కం
    -0.07
     wafer
    -0.07
    -direct
    -0.07
     csrf
    -0.07
    ilda
    -0.07
     octave
    -0.07
    POSITIVE LOGITS
     hikers
    0.14
     randonnée
    0.13
     wilderness
    0.11
     hiking
    0.11
    Camping
    0.11
     Camping
    0.10
     অভিযান
    0.10
     emergencies
    0.10
     Garmin
    0.10
    Emergency
    0.10
    Activations Density 0.082%

    No Known Activations