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. 55662
    Prev
    Next
    INDEX
    Explanations

    colons

    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
     gall
    -0.08
    rowing
    -0.08
     prim
    -0.08
     nursing
    -0.08
     బాల
    -0.07
    phon
    -0.07
    -moving
    -0.07
    omial
    -0.07
     бу
    -0.07
     మొ
    -0.07
    POSITIVE LOGITS
     ```↵
    0.08
     quartz
    0.08
     pant
    0.07
     malt
    0.07
    've
    0.07
    Firstly
    0.07
     واج
    0.07
    Orientation
    0.07
     Should
    0.07
     Sah
    0.07
    Activations Density 0.101%

    No Known Activations