© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 99624
    Prev
    Next
    INDEX
    Explanations

    tantrums

    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
     Malmö
    -0.08
     percor
    -0.08
     latt
    -0.08
     stumbled
    -0.08
     lato
    -0.08
     siden
    -0.08
    াউ
    -0.08
     pelle
    -0.08
    ರ್�
    -0.08
     hyperlink
    -0.08
    POSITIVE LOGITS
    哭
    0.14
     tantr
    0.12
     agitation
    0.12
     whining
    0.11
     soothe
    0.10
     शांत
    0.10
     crying
    0.10
     agit
    0.10
     soothing
    0.10
     angry
    0.10
    Activations Density 0.053%

    No Known Activations