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. 76976
    Prev
    Next
    INDEX
    Explanations

    axioms and logic

    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
     canyon
    -0.08
    gun
    -0.08
     backpack
    -0.07
    payi
    -0.07
     Backpack
    -0.07
    igeze
    -0.07
    Cargo
    -0.07
    Website
    -0.07
    ifiquement
    -0.07
     صنعت
    -0.07
    POSITIVE LOGITS
     premises
    0.17
     assumptions
    0.16
     premise
    0.16
     Fakten
    0.15
     facts
    0.15
     assumption
    0.14
     fatos
    0.13
    事实
    0.13
     axi
    0.13
     truths
    0.13
    Activations Density 0.040%

    No Known Activations