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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 47785
    Prev
    Next
    INDEX
    Explanations

    placing blame

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     credit
    -0.10
     goude
    -0.09
    credited
    -0.09
     dator
    -0.09
    ower
    -0.09
     corte
    -0.09
     Credit
    -0.09
    OWER
    -0.08
     ieg
    -0.08
     કોર
    -0.08
    POSITIVE LOGITS
    Nev
    0.08
    (ac
    0.08
    指
    0.08
    (ex
    0.08
     İnsan
    0.08
    #ac
    0.08
     Kullan
    0.07
    Accommodation
    0.07
     Sadd
    0.07
     aceite
    0.07
    Activations Density 0.013%

    No Known Activations