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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 65420
    Prev
    Next
    INDEX
    Explanations

    de-escalation

    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
    ssd
    -0.08
     �
    -0.07
    terno
    -0.07
     RL
    -0.07
     fleeting
    -0.07
     परिवार
    -0.07
     여
    -0.07
    170
    -0.07
     Goods
    -0.07
    _Pl
    -0.07
    POSITIVE LOGITS
     riesgos
    0.09
     অহ
    0.09
    毒
    0.09
     undue
    0.09
     riscos
    0.08
    angana
    0.08
     toxic
    0.08
    ijkstra
    0.08
     iverm
    0.08
     amel
    0.08
    Activations Density 0.011%

    No Known Activations