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. 67265
    Prev
    Next
    INDEX
    Explanations

    far

    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
     heutzutage
    -0.09
     mulighed
    -0.08
    guru
    -0.08
     tegenwoordig
    -0.07
    ested
    -0.07
    tml
    -0.07
     préd
    -0.07
     된다
    -0.07
    нули
    -0.07
    ulia
    -0.07
    POSITIVE LOGITS
    以来
    0.10
    看来
    0.09
     sharp
    0.08
    varande
    0.08
     incarnation
    0.08
     belum
    0.08
     અત્યાર
    0.08
    �
    0.08
     bisherigen
    0.08
    ,the
    0.08
    Activations Density 0.017%

    No Known Activations