© 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. 68619
    Prev
    Next
    INDEX
    Explanations

    risks and consequences

    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
    _sigma
    -0.09
     :)↵
    -0.08
     :-)↵
    -0.08
     sigma
    -0.08
     sukses
    -0.08
    gata
    -0.08
     miracle
    -0.08
    jg
    -0.08
     grazie
    -0.08
    isdigit
    -0.07
    POSITIVE LOGITS
     detrimental
    0.16
     debilitating
    0.14
     consequences
    0.13
     jeopard
    0.12
     adversely
    0.12
     repercussions
    0.12
     conséquences
    0.12
     تؤ
    0.12
     underm
    0.12
     worse
    0.11
    Activations Density 0.135%

    No Known Activations