© 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. 19-RESID-POST-AA
    11. 102356
    Prev
    Next
    INDEX
    Explanations

    "to each according to"

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Resume
    -0.08
     또는
    -0.07
    .There
    -0.07
     (--
    -0.07
     _
    -0.07
    また
    -0.07
     or
    -0.07
     `
    -0.07
    .Commands
    -0.07
     resume
    -0.07
    POSITIVE LOGITS
    לעכע
    0.09
    ichtigkeit
    0.09
     handling
    0.09
    لبية
    0.09
    熟妇
    0.09
     HANDLE
    0.09
    abulous
    0.09
    Nós
    0.09
     баһ
    0.08
    ӡ
    0.08
    Activations Density 0.000%

    No Known Activations