© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 1331
    Prev
    Next
    INDEX
    Explanations

    backward

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    datatable
    -0.08
    frm
    -0.08
     outlet
    -0.08
     Nyt
    -0.08
     Sect
    -0.08
    IHE
    -0.08
    'exp
    -0.07
     experimentation
    -0.07
    -white
    -0.07
     limitée
    -0.07
    POSITIVE LOGITS
     backwards
    0.12
     backward
    0.10
    Backward
    0.09
     dulu
    0.08
    Christine
    0.08
     reverse
    0.08
     trás
    0.08
     recursively
    0.08
     firstly
    0.08
     времен
    0.08
    Activations Density 0.013%

    No Known Activations