Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 130758
    Prev
    Next
    INDEX
    Explanations

    escalation

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prém
    -0.09
     finalized
    -0.09
    व्ह
    -0.08
     anay
    -0.08
    ань
    -0.08
     chod
    -0.07
    vý
    -0.07
    hk
    -0.07
    Receive
    -0.07
    št
    -0.07
    POSITIVE LOGITS
     escalation
    0.16
     escal
    0.16
    -es
    0.15
    _es
    0.14
     Esc
    0.14
     escalate
    0.14
     escalating
    0.13
    Esc
    0.13
     esk
    0.12
     es
    0.12
    Activations Density 0.001%

    No Known Activations