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. 45125
    Prev
    Next
    INDEX
    Explanations

    Stabil

    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
     aufgenommen
    -0.08
     recording
    -0.08
    .Pos
    -0.08
     meinte
    -0.08
     prerecorded
    -0.08
    ിച്ചത്
    -0.08
    _IDLE
    -0.08
     मे
    -0.08
     данной
    -0.08
     XVIII
    -0.08
    POSITIVE LOGITS
    뒤
    0.08
     ruby
    0.07
    어요
    0.07
     Boulder
    0.07
    ruby
    0.07
     tə
    0.07
     involves
    0.07
     bulld
    0.07
     Olaf
    0.07
    )=>{↵
    0.07
    Activations Density 0.001%

    No Known Activations