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. 3-RESID-POST-AA
    6. 12390
    Prev
    Next
    INDEX
    Explanations

    -ing form verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     screaming
    -0.07
     slice
    -0.07
     Pig
    -0.07
    263
    -0.07
     pancakes
    -0.07
    uż
    -0.07
     lanes
    -0.07
     allen
    -0.07
     competitions
    -0.07
     cum
    -0.07
    POSITIVE LOGITS
     놓
    0.10
     터
    0.09
    저
    0.09
     Honour
    0.08
     judgement
    0.08
    Gt
    0.08
     প্রয়
    0.08
    нё
    0.08
    ിര്
    0.08
     바라
    0.07
    Activations Density 0.115%

    No Known Activations