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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 108913
    Prev
    Next
    INDEX
    Explanations

    ’s

    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
    ersch
    -0.08
     Lo
    -0.08
    inks
    -0.07
    ательная
    -0.07
    dcc
    -0.07
    ektedir
    -0.07
    이며
    -0.07
    fern
    -0.07
    íonn
    -0.07
    회
    -0.07
    POSITIVE LOGITS
     vào
    0.13
     туда
    0.12
     into
    0.12
     pọ
    0.10
    Into
    0.10
     silẹ
    0.10
    into
    0.09
     сюда
    0.09
    _into
    0.09
     Into
    0.09
    Activations Density 0.730%

    No Known Activations