© 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. 11-RESID-POST-AA
    11. 7807
    Prev
    Next
    INDEX
    Explanations

    Trinity

    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
     sorted
    -0.08
     tah
    -0.07
     nearing
    -0.07
    337
    -0.07
    Sorted
    -0.07
     optimistic
    -0.07
     sequences
    -0.07
     Reach
    -0.07
     通
    -0.07
     ordenar
    -0.07
    POSITIVE LOGITS
     indiv
    0.09
     يجوز
    0.09
     obedience
    0.09
    brevi
    0.08
    իպ
    0.08
     obedient
    0.08
     Hebrews
    0.08
    _Property
    0.08
     cape
    0.08
     quid
    0.08
    Activations Density 0.015%

    No Known Activations