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. 53178
    Prev
    Next
    INDEX
    Explanations

    systems

    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
     wherever
    -0.07
    !!
    -0.07
     từng
    -0.07
     которой
    -0.07
    ??
    -0.07
    ???
    -0.07
     Pact
    -0.07
    Confirm
    -0.07
    Recover
    -0.07
     phía
    -0.07
    POSITIVE LOGITS
     heutzutage
    0.11
     tegenwoordig
    0.10
     бывают
    0.10
    typically
    0.09
    通常
    0.09
     عادة
    0.09
     Typically
    0.09
     généralement
    0.08
     зачастую
    0.08
     typically
    0.08
    Activations Density 0.136%

    No Known Activations